Partner Basecamp · Cohort 7

Function	Practitioner	Sr Practitioner	Mgr / Sr Mgr	Director+	Partner / MD	Total
Engineering	6	7	6	2	–	21
Architecture	1	2	4	5	–	12
Business Leadership	–	–	2	6	2	10
Project / Engmt	4	4	10	3	1	22

Segment	Exploring	Applying	Delivering	Frontier	n
Transformation Lead	15%	62%	15%	8%	39
Developer	8%	69%	23%	—	13
Architect	15%	38%	38%	8%	13

Segment	Exploring	Applying	Delivering	Frontier	n
Manager or Senior Manager	18%	59%	18%	5%	22
Director, Senior Director, or Principal	6%	44%	31%	19%	16
Senior practitioner (5–9 years)	8%	77%	15%	—	13
Practitioner (0-4 years in role)	18%	64%	18%	—	11
Partner, Managing Director, or Executive	33%	33%	33%	—	3

Segment	Too basic	About right	Too advanced	n
Transformation Lead	8%	79%	13%	39
Developer	8%	92%	—	13
Architect	23%	77%	—	13

Segment	Too basic	About right	Too advanced	n
Applying in practice	5%	87%	8%	38
Delivering independently	21%	79%	—	14
Learning and exploring	—	78%	22%	9
Operating at the frontier	50%	50%	—	4

Segment	Too slow	Well paced	Too fast	n
Transformation Lead	3%	87%	10%	39
Developer	—	100%	—	13
Architect	8%	92%	—	13

Segment	Too slow	Well paced	Too fast	n
Applying in practice	3%	92%	5%	38
Delivering independently	—	100%	—	14
Learning and exploring	—	78%	22%	9
Operating at the frontier	25%	75%	—	4

How likely are you to recommend attending this programme to a colleague?

n=59 Day 2 respondents · 91% of Day 1

Score distribution · 0 = not at all likely · 10 = extremely likely

Cohort	0	1	2	3	4	5	6	7	8	9	10
Cohort 7					2	5	6	3	12	10	21

■ Detractors 0–6■ Passives 7–8■ Promoters 9–10

NPS Breakdown

52%

25%

22%

NPS +31 (n=59)

Promoters (9–10)Passives (7–8)Detractors (0–6)

Programme mean: +41 · 3 cohorts

Promoters mean: 52%

Passives mean: 36%

Detractors mean: 11%

NPS by Segment

Organisations, personas, and experience levels · ≥4 respondents shown

By Organisation

Promoters (9–10)Passives (7–8)Detractors (0–6)

Accenture

73%

27%

NPS +73 (n=11)

Deloitte

69%

23%

NPS +62 (n=13)

Infosys

40%

20%

NPS +20 (n=5)

Cognizant

29%

43%

NPS -14 (n=7)

PwC

18%

64%

NPS -45 (n=11)

By Persona

Promoters (9–10)Passives (7–8)Detractors (0–6)

Unknown

60%

30%

10%

NPS +50 (n=10)

Transformation Lead

57%

18%

25%

NPS +32 (n=28)

Developer

50%

20%

30%

NPS +20 (n=10)

Architect

36%

46%

18%

NPS +18 (n=11)

Programme means · 3 cohorts: Architect +74 · Transformation Lead +44 · Developer +42

By AI Experience Level

Promoters (9–10)Passives (7–8)Detractors (0–6)

Operating at the frontier

75%

25%

NPS +75 (n=4)

Delivering independently

70%

20%

10%

NPS +60 (n=10)

Applying in practice

45%

24%

31%

NPS +14 (n=29)

Learning and exploring

33%

NPS 0 (n=6)

Programme means · 3 cohorts: Learning and exploring +64 · Delivering independently +55 · Operating at the frontier +48 · Applying in practice +31

What is the main reason for your score?

n=51 responses · organised by NPS segment

Promoters (score 9–10)· 25 responses

Solid for baselining people across the skill.

10“Content was great. Presenters were knowledgeable and very helpful. Exercises focused on the content they just covered with time to experiment . Course length a d breaks were well times Thanks”

Passives (score 7–8)· 13 responses

Would like more build guidance instead of working off pre built plumbing

8“In comparison with Microsoft AI-300 , the content of the course being taught is level above. While Microsoft AI-300 teaches me evaluations, tracing at each pipelines and the differential factors , Claude touches on evaluations but it doesn’t touch on what causes latency and throughput and each pipeline tasks.”

Detractors (score 0–6)· 13 responses

The online modules are nice. The working modules in the workshop are something one can do on their own and need not be done in person. There was no big insight

4“I found the training helpful for a few takeaways / tips but not much more broadly. I understand the challenge in crafting the exercises but I thought they were too advanced for someone who comes in knowing nothing but too basic for someone who comes in having foundational knowledge. I found the Jupyter notebooks confusing to use, and the instructors weren't clear until speaking to them 1:1 that the preferred method was to run it directly in Claude Code or VS Code. Additionally, none of the instructions were written for the desktop Claude Code. The first exercise that had instructions in a site directly (https://claude-code-workshop.netlify.app/) was by far the best, and I would have loved if the other exercises were the same. The 02 and 03 exercises on Day 2 in particular, were not very helpful. For 02 especially, there was nothing actually to DO because it ran on its own and I didn't understand what the takeaway was supposed to be. Our table finished in just a few minutes and chatted instead because there was nothing else to do for that exercise. In general across the exercises, I didn't understand the right balance of what to ask Claude to do directly, versus what we should do ourselves. I liked that in the 04 exercise on Day 1 they told us more explicitly when to digest ourselves vs. when to use Claude. Because Claude could do the exercises itself, I felt like I didn't necessarily grasp the takeaways. I think the Agent Build at the end of Day 2 was one of the better exercises, but for all of them, there was a lot already built / a lot of code already written, which personally made it more confusing. Since I have less coding experience, I didn't know what to read / how to understand a good amount of what was in the Jupyter notebooks. There were parts to fill in that seemed to require Python knowledge or understanding of the data structure. While I was able to move forward by talking to Claude, it felt like it defeated the purpose of the exercise. I also really liked the evals conversation and exercise, and it was where I felt like I learned the most. However, it wasn't made clear how/where to implement the eval in a real world use case. Do you build a site? When does the eval check get run? It would have been helpful to connect back to use cases and when to literally put an eval into practice and how. Finally, this is super small and I'm sure unintentional, but I was doing an initial group share with a group of other women and one of the facilitators came to chat with us. She spoke to us with the assumption that we didn't know anything about Github/development, despite us not having shared that. It felt like because we were a group of women, it was assumed that we were on the lower end of experience, when in fact that was not true. Again, she shared helpful tips (which may have been shared with other groups as well), it just struck me as odd. It was also surprising to me, and the other participants I spoke to about this, that none of the facilitators worked at Anthropic. It felt like it was billed as an Anthropic-run training and the facilitators were purposefully vague about it. I think it would have been better if there was more transparency there! The facilitators were still helpful and knowledgeable, and Claude directly was able to do almost all troubleshooting anyways.”

1	2	3	4	5	Mean
—	—	19%	34%	47%	4.29

1	2	3	4	5	Mean
—	—	15%	41%	44%	4.29

1	2	3	4	5	Mean
—	3%	14%	46%	37%	4.17

NPS Reason

n=51 responses · grouped by NPS segment

Promotersscore 9–10 · 25 responses

1Very helpful for a beginner10

2Great practical session10

3Learnt new things and hearing about others’ experiences with Claude really helps think out of the box.10

4Very informative10

5Actually useful contents10

6Eye opening , clarity of thoughts in positioning Claude to customers10

7New knowldgr10

8Learned new ways to fully get full power of Claude10

9The contents, instructors and hands on exercises were greatly managed10

10Very engaging and practical experience10

11Great session10

12It was well taught, attentive to details and folks were always present to support individuals. I think everyone could benefit from this program regardless of their AI literacy.10

13hands on is valuable10

14Content was great. Presenters were knowledgeable and very helpful. Exercises focused on the content they just covered with time to experiment . Course length a d breaks were well times Thanks10

15We could deeply learn about agent development, especially in context engineering and evaluations10

16Solid for baselining people across the skill.9

17Great learning on latest features and capabilities9

18Day 1 was introductory. Can be split into a different session.9

19Staff was very helpful, I learned a lot9

20Content I have not seen elsewhere by Anthropic in training9

21Great hands-on exercises9

22Enjoyed the class9

23Great content and learning opportunity9

24Engaging content and the hands on practicals9

25It gives a holistic view kf clause enterprises and also build along using it which helps in curating real use cases9

Passivesscore 7–8 · 13 responses

1Na8

2Good course8

3Not as advanced as I would have liked.8

4It will be useful to learn new things8

5Good8

6I work primarily with engineers and think this would be a good course for them to get deeper into Claude. I do think that there were a few too many exercises and would rather have digested a bit more in between. I think it would be helpful to discuss the solutions more in depth8

7Lots of hands on session which helped to understand and playground with Claude code.8

8Good experience and able interaction with more people and share the knowledge8

9In comparison with Microsoft AI-300 , the content of the course being taught is level above. While Microsoft AI-300 teaches me evaluations, tracing at each pipelines and the differential factors , Claude touches on evaluations but it doesn’t touch on what causes latency and throughput and each pipeline tasks.8

10Good hands on session - but didn't cover the aspects of using AI and claude in specific in solving real world problems8

11Would like more build guidance instead of working off pre built plumbing7

12I learned a lot of things via this training, but Japanese people may struggle to learn because of English skill.7

13Content is good; Anthropic staff helpful7

Detractorsscore 0–6 · 13 responses

1The online modules are nice. The working modules in the workshop are something one can do on their own and need not be done in person. There was no big insight6

2Its is good for entry level with no claude code experience6

3The workshop could have been more real world practice. Like actually solving by real world problems.6

4I feel that a lot of the topics were not new and well known topics. If someone was new this would be good to learn the concept but someone who knows the concepts it was very much repetitive. Also think there could be more talk and discussion then sitting and doing individual hands on labs.6

5I think this felt more of an introduction to how to use Claude and while hit on technical topics the way it was delivered felt more like copy and paste or execute this juniper notebook vs explaining the concepts and why we would do certain things.6

6While informative, I think it was somewhat narrowly focused on the engineering aspect. Many of us are not engineers, and might benefit from less technical building and more around what is possible. Clients are not asking us about how to troubleshoot their agents, but rather how can they use AI to help to begin with.6

7There is an opportunity to make the training facilitate more dialogue and discussion. This one focused a lot on heads down coding that can be pre-work/virtual work.5

8Understanding of python code is required to make this session useful. It's not really for non technical people5

9Training is not hands on or intuitive for non-tech folks. There have to be atleast one hands on to ensure the business and sales folks can harness the power of agentification in code form in Claude code or vscode5

10Session should have been focused more on particular role instead of focusing multiple roles, I feel not completely focus on presentation to client , not completely developer oriented5

11The early demos were very complex and hard to follow when jumping in. Additionally, they required additional set up steps. Several demos and workshops labs didn’t work immediately and required Claude to troubleshoot and fix. This took the focus away from the specific skills being taught in each lab5

12I found the training helpful for a few takeaways / tips but not much more broadly. I understand the challenge in crafting the exercises but I thought they were too advanced for someone who comes in knowing nothing but too basic for someone who comes in having foundational knowledge. I found the Jupyter notebooks confusing to use, and the instructors weren't clear until speaking to them 1:1 that the preferred method was to run it directly in Claude Code or VS Code. Additionally, none of the instructions were written for the desktop Claude Code. The first exercise that had instructions in a site directly (https://claude-code-workshop.netlify.app/) was by far the best, and I would have loved if the other exercises were the same. The 02 and 03 exercises on Day 2 in particular, were not very helpful. For 02 especially, there was nothing actually to DO because it ran on its own and I didn't understand what the takeaway was supposed to be. Our table finished in just a few minutes and chatted instead because there was nothing else to do for that exercise. In general across the exercises, I didn't understand the right balance of what to ask Claude to do directly, versus what we should do ourselves. I liked that in the 04 exercise on Day 1 they told us more explicitly when to digest ourselves vs. when to use Claude. Because Claude could do the exercises itself, I felt like I didn't necessarily grasp the takeaways. I think the Agent Build at the end of Day 2 was one of the better exercises, but for all of them, there was a lot already built / a lot of code already written, which personally made it more confusing. Since I have less coding experience, I didn't know what to read / how to understand a good amount of what was in the Jupyter notebooks. There were parts to fill in that seemed to require Python knowledge or understanding of the data structure. While I was able to move forward by talking to Claude, it felt like it defeated the purpose of the exercise. I also really liked the evals conversation and exercise, and it was where I felt like I learned the most. However, it wasn't made clear how/where to implement the eval in a real world use case. Do you build a site? When does the eval check get run? It would have been helpful to connect back to use cases and when to literally put an eval into practice and how. Finally, this is super small and I'm sure unintentional, but I was doing an initial group share with a group of other women and one of the facilitators came to chat with us. She spoke to us with the assumption that we didn't know anything about Github/development, despite us not having shared that. It felt like because we were a group of women, it was assumed that we were on the lower end of experience, when in fact that was not true. Again, she shared helpful tips (which may have been shared with other groups as well), it just struck me as odd. It was also surprising to me, and the other participants I spoke to about this, that none of the facilitators worked at Anthropic. It felt like it was billed as an Anthropic-run training and the facilitators were purposefully vague about it. I think it would have been better if there was more transparency there! The facilitators were still helpful and knowledgeable, and Claude directly was able to do almost all troubleshooting anyways.4

13There were a great number of flaws in the notebooks, little instruction, and we did not receive accurate setup instructions prior to being onsite. The main response from facilitators was “ask Claude”. I’m not certain in that case the purpose of being onsite. I would suggest more robust setup instructions including all the dependencies we need. I would also recommend reviewing all trainings and fixing the major issues. Some had issues in the very first cell because someone forgot to install the necessary dependencies before importing a module. There was also far too many variables involved. If we used Claude through VS Code or CodeSpaces as suggested, we’d run into rate limit issues from Git. Using the native Claude Code application didn’t have the same views of directories. We were supposed to set up Claude Cowork but never did anything with it. There is apparently a certification involved with this and we got no information about it at any point across the past two days.4

Most Valuable

What one takeaway will you share with a colleague or client? · n=38 responses

1Models are highly capable by themselves what matters are the surrounding implementations- cost management , evaluations , context engineering , model selection

2Na

3Evals learnings

4Keep learning and stay updated

5How Ai agents and other tools within the ecosystem work

6It’s not as scary as I thought

7The only limit is our imagination

8AI

9Claude can be used in multiple ways depending on who is needing it

10Start buying Claude personal account

11Using evals to judge responses

12The importance of Evals

13Learn how to plan before implementing No swag ;( Please provide channel of communication.

14The models are production ready and let’s go!

15Evals

16Latency and cost are a big talking point

17The focus on prompt engineering and evals are even more important and often overlooked

18Claude for all

19Great course for intro to Claude

20Model is just commodity and we should focus more on application layer and engineering

21Claude is amazing, just ask if you’re not sure. No question is too silly

22Good

23Agent building

24Better preparation is recommended and some technical know how

25Please get a discord chat so we can share messages, output, results, etc. Communication would be a great way of sharing

26Very interesting ways to utilize a tool like this.

27Learn more on AI

28Agent harness, inference troubleshooting. One of my favorite and new topics. Thank you.

29Good one, wanted more of detailed information

30You can make a flexible agent

31How it will benefit for the team.

32Everyone needs to now be able to build using AI and claude is where the buck stops. The capabilities are amazing and we just touched the tip of iceberg here

33How we can leverage Claude to produce faster with better cost optimization

34Methodology of eval

35・The importance and best practice of context engineering ・how to evaluate agents, like code, llm as a judge or human fb

36Na

37Using evals! Deterministic vs LLM evals

38Other feedback: Multiple people on my team have dietary restrictions. When we had our alliance reach out, we were told that you wouldn’t be taking dietary restrictions because there were a variety of food options in the Ferry Building. It sounded as if we’d be eating from places in the Ferry Building, not that you were catering and instead meant “we are not taking anyone’s dietary restrictions into account and you’ll have to buy your own food if you have them”. Myself and another team member were not able to eat breakfast or lunch the first day at all. It was highly unpleasant and we would have made other arrangements if it had been clear you do not make accommodations.

Suggestions to Improve

What would have made today even better? · n=51 responses

1The online modules are nice. The working modules in the workshop are something one can do on their own and need not be done in person. There was no big insight

2Na

3Solid for baselining people across the skill.

4Very helpful for a beginner

5Great practical session

6Good course

7Learnt new things and hearing about others’ experiences with Claude really helps think out of the box.

8Great learning on latest features and capabilities

9Very informative

10Would like more build guidance instead of working off pre built plumbing

11Actually useful contents

12Its is good for entry level with no claude code experience

13Day 1 was introductory. Can be split into a different session.

14Staff was very helpful, I learned a lot

15Eye opening , clarity of thoughts in positioning Claude to customers

16New knowldgr

17Learned new ways to fully get full power of Claude

18Not as advanced as I would have liked.

19There is an opportunity to make the training facilitate more dialogue and discussion. This one focused a lot on heads down coding that can be pre-work/virtual work.

20The workshop could have been more real world practice. Like actually solving by real world problems.

21The contents, instructors and hands on exercises were greatly managed

22Understanding of python code is required to make this session useful. It's not really for non technical people

23I feel that a lot of the topics were not new and well known topics. If someone was new this would be good to learn the concept but someone who knows the concepts it was very much repetitive. Also think there could be more talk and discussion then sitting and doing individual hands on labs.

24Content I have not seen elsewhere by Anthropic in training

25Very engaging and practical experience

26I think this felt more of an introduction to how to use Claude and while hit on technical topics the way it was delivered felt more like copy and paste or execute this juniper notebook vs explaining the concepts and why we would do certain things.

27It will be useful to learn new things

28Great hands-on exercises

29Good

30I work primarily with engineers and think this would be a good course for them to get deeper into Claude. I do think that there were a few too many exercises and would rather have digested a bit more in between. I think it would be helpful to discuss the solutions more in depth

31Lots of hands on session which helped to understand and playground with Claude code.

32Great session

33Training is not hands on or intuitive for non-tech folks. There have to be atleast one hands on to ensure the business and sales folks can harness the power of agentification in code form in Claude code or vscode

34Enjoyed the class

35Great content and learning opportunity

36Good experience and able interaction with more people and share the knowledge

37It was well taught, attentive to details and folks were always present to support individuals. I think everyone could benefit from this program regardless of their AI literacy.

38While informative, I think it was somewhat narrowly focused on the engineering aspect. Many of us are not engineers, and might benefit from less technical building and more around what is possible. Clients are not asking us about how to troubleshoot their agents, but rather how can they use AI to help to begin with.

39In comparison with Microsoft AI-300 , the content of the course being taught is level above. While Microsoft AI-300 teaches me evaluations, tracing at each pipelines and the differential factors , Claude touches on evaluations but it doesn’t touch on what causes latency and throughput and each pipeline tasks.

40hands on is valuable

41Engaging content and the hands on practicals

42It gives a holistic view kf clause enterprises and also build along using it which helps in curating real use cases

43Content was great. Presenters were knowledgeable and very helpful. Exercises focused on the content they just covered with time to experiment . Course length a d breaks were well times Thanks

44I learned a lot of things via this training, but Japanese people may struggle to learn because of English skill.

45We could deeply learn about agent development, especially in context engineering and evaluations

46Good hands on session - but didn't cover the aspects of using AI and claude in specific in solving real world problems

47Session should have been focused more on particular role instead of focusing multiple roles, I feel not completely focus on presentation to client , not completely developer oriented

48The early demos were very complex and hard to follow when jumping in. Additionally, they required additional set up steps. Several demos and workshops labs didn’t work immediately and required Claude to troubleshoot and fix. This took the focus away from the specific skills being taught in each lab

49Content is good; Anthropic staff helpful

50I found the training helpful for a few takeaways / tips but not much more broadly. I understand the challenge in crafting the exercises but I thought they were too advanced for someone who comes in knowing nothing but too basic for someone who comes in having foundational knowledge. I found the Jupyter notebooks confusing to use, and the instructors weren't clear until speaking to them 1:1 that the preferred method was to run it directly in Claude Code or VS Code. Additionally, none of the instructions were written for the desktop Claude Code. The first exercise that had instructions in a site directly (https://claude-code-workshop.netlify.app/) was by far the best, and I would have loved if the other exercises were the same. The 02 and 03 exercises on Day 2 in particular, were not very helpful. For 02 especially, there was nothing actually to DO because it ran on its own and I didn't understand what the takeaway was supposed to be. Our table finished in just a few minutes and chatted instead because there was nothing else to do for that exercise. In general across the exercises, I didn't understand the right balance of what to ask Claude to do directly, versus what we should do ourselves. I liked that in the 04 exercise on Day 1 they told us more explicitly when to digest ourselves vs. when to use Claude. Because Claude could do the exercises itself, I felt like I didn't necessarily grasp the takeaways. I think the Agent Build at the end of Day 2 was one of the better exercises, but for all of them, there was a lot already built / a lot of code already written, which personally made it more confusing. Since I have less coding experience, I didn't know what to read / how to understand a good amount of what was in the Jupyter notebooks. There were parts to fill in that seemed to require Python knowledge or understanding of the data structure. While I was able to move forward by talking to Claude, it felt like it defeated the purpose of the exercise. I also really liked the evals conversation and exercise, and it was where I felt like I learned the most. However, it wasn't made clear how/where to implement the eval in a real world use case. Do you build a site? When does the eval check get run? It would have been helpful to connect back to use cases and when to literally put an eval into practice and how. Finally, this is super small and I'm sure unintentional, but I was doing an initial group share with a group of other women and one of the facilitators came to chat with us. She spoke to us with the assumption that we didn't know anything about Github/development, despite us not having shared that. It felt like because we were a group of women, it was assumed that we were on the lower end of experience, when in fact that was not true. Again, she shared helpful tips (which may have been shared with other groups as well), it just struck me as odd. It was also surprising to me, and the other participants I spoke to about this, that none of the facilitators worked at Anthropic. It felt like it was billed as an Anthropic-run training and the facilitators were purposefully vague about it. I think it would have been better if there was more transparency there! The facilitators were still helpful and knowledgeable, and Claude directly was able to do almost all troubleshooting anyways.

51There were a great number of flaws in the notebooks, little instruction, and we did not receive accurate setup instructions prior to being onsite. The main response from facilitators was “ask Claude”. I’m not certain in that case the purpose of being onsite. I would suggest more robust setup instructions including all the dependencies we need. I would also recommend reviewing all trainings and fixing the major issues. Some had issues in the very first cell because someone forgot to install the necessary dependencies before importing a module. There was also far too many variables involved. If we used Claude through VS Code or CodeSpaces as suggested, we’d run into rate limit issues from Git. Using the native Claude Code application didn’t have the same views of directories. We were supposed to set up Claude Cowork but never did anything with it. There is apparently a certification involved with this and we got no information about it at any point across the past two days.

30-Day Intentions

What will you build for yourself or apply at work? · n=47 responses

11. Build - design and implement agentic system for solutions 2. Reimagine the BPO operating model

2Developer prod

3GRC tools

4Many agents

5Yes

6A local knowledge graph that can pull content together from various historical decks.

7Full agentic applications

8Custom apps

9poc for client.

10I will build a dashboard for a client to help decision making.

11Create RFP moderater

12Continue to iterate on current projects and client accelerators

13Multi-agent architecture

14Agent to help with daily task

15I’ll develop agents to help my tasks better and efficient

16Converting user story to agentic tasks

17Multiple Projects

18Personal website to show professional journey and interests

19Build a marketing platform run by a team of agents

20A dashboard for my work which will help in taking decisions on a day to day basis.

21Operations analytics dashboard

22Applying AI agents into workflows

23Evaluations

24Build and define custom agents with improvised controls for my application

25Looking to build a personal assistant agent and hoping to be able to leverage co-work when available on enterprise license.

26Internal utilities - couple of agents to do my day to day job

27Delivery tools to help project teams and GTM materials to help us sell more work

28Agents

29Build agents for Pharma company

30Agents

31I plan to build agents for regular tasks , RFP questions, RFP solutions, that help me become more productive

32So many things. Building 5 different ideas now, why wait

33Migration tool for integration solutions

34Continue to use AI skills for POC and Proposals

35We’re building a firm-wide Skills marketplace that works downstream and upstream. What I’m excited to work on is implementing Evals against those skills and improve them at scale. One step at a time.

36Revisions to our current multi agent tool used internally to help us deliver to our clients.

37Presentation, building smart agents for detections.

38Will make the agent for myself to brainstorm

39Service now tickets automatic response and the resolution notes updation

40Mainly build using claude and also understand the cost and tokens around the models to have discussion with clients

41I’m working on an energy trading app. This course will help me finish faster so I can demo to our client faster and provide additional context on the approach using AI

42I will try to effort to make my company's enablement higher.

43Multi agent chat-based application for development and knowledge search with Strands SDK and Claude on bedrock

44Na

45Automate community building tasks

46I want to implement a routine (this was briefly shared in the "What's New" section and this is a feature I am super excited for) based on our Github tickets.

47I did appreciate that it got me working in code and a bit of time to play around. After the issues with setup, I did understand how to use it better. The prompt engineering and eval workshops were the best.

San Francisco