AWSKnown publisherawslabs/startups/migrate/plugins/migration-to-aws/fixtures/agent-advisor-openai-demo/CLAUDE.mdstartups / agent-advisor-openai-demo
CLAUDE.md25 starsChanged 44 days agoApache-2.0View on GitHub
Existing OpenAI customer-support bot. - src/support_bot/agent.py: classifies tickets with GPT-4o (Chat Completions) and deep-reasons with GPT-5.4 (Responses API). - src/support_bot/extras.py: audio transcription (whisper-1), embeddings (text-embedding-3-large), hosted file search (gpt-5.4 + file_search). - Sessions last 10-20 minutes; traffic is bursty. - Low operational overhead preferred; no Kubernetes requirement. - API continuity: required — preserve the OpenAI SDK and API surface. - Priority: balanced (cost vs capability). - Governance: none — no Bedrock Guardrails, invocation logging, or multi-model Converse requirement. - Target…
In this repository23 other files it gives its agents.
- advisor/AGENTS.mdAGENTS.md
- agent-advisorSkill
- architect-for-startupsSkill
- azure-to-awsSkill
- contextual-offers-for-startupsSkill
- gcp-to-awsSkill
- heroku-to-awsSkill
- knowledge-base-for-startupsSkill
- llm-to-bedrockSkill
- prompt-library-for-startupsSkill
- start-building-for-startupsSkill
- tf-best-practicesSkill
- agent-advisorSkill
- azure-to-awsSkill
- gcp-to-awsSkill
- heroku-to-awsSkill
- llm-to-bedrockSkill
- tf-best-practicesSkill
- agentcore-patternsSkill
- cost-regression-checkSkill
- hcls-stack-checkSkill
- multi-tenant-isolationSkill
- self-hosted-llm-batch-inferenceSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
No AWS account yet; live verification = not_run.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Support-bot fixture — migration requirements
Existing OpenAI customer-support bot.
src/support_bot/agent.py: classifies tickets with GPT-4o (Chat Completions) and deep-reasons with GPT-5.4 (Responses API).src/support_bot/extras.py: audio transcription (whisper-1), embeddings (text-embedding-3-large), hosted file search (gpt-5.4 + file_search).- Sessions last 10-20 minutes; traffic is bursty.
- Low operational overhead preferred; no Kubernetes requirement.
Requirements (authoritative)
- API continuity: required — preserve the OpenAI SDK and API surface.
- Priority: balanced (cost vs capability).
- Governance: none — no Bedrock Guardrails, invocation logging, or multi-model Converse requirement.
- Target region: us-east-2.
- No AWS account yet; live verification = not_run.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.