MicrosoftKnown publishermicrosoft/aitour27-BRK390-building-ai-applications-with-microsoft-databases-and-fabric/AGENTS.mdaitour27-BRK390-building-ai-applications-with-microsoft-databases-and-fabric
AGENTS.md1 starsChanged 51 days agoMITView on GitHub
This repository contains the full BRK390 session. The publication responsibility covered here is the Act 3 demo under instructions/act3.md, docs/act3.md, infra/act3/, scripts/act3/, src/act3/, and the directly related tests and SQL runtime file. 1. Read docs/act3.md and instructions/act3.md. 2. Read .github/skills/caldova-demo/SKILL.md. 3. Keep data/scenario.json frozen and derive the December staffing scenario through scripts/act3/build-staffing-scenario.mjs. 4. Use Node.js 24 or later. TypeScript runs through native type stripping; do not add a TypeScript compilation step. - Treat every business record as synthetic and every…
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- microsoft/frontiertour27-BRK390-building-ai-applications-with-microsoft-databases-and-fabricword for word, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 1
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- src/caldova-insights/AGENTS.mdAGENTS.md
- caldova-demoSkill
- demo-security-reviewSkill
- caldova-campaign-planningSkill
- app-designSkill
- app-validationSkill
- dax-authoringSkill
- fabric-cliSkill
- fabric-sdkSkill
- playwright-cliSkill
- query-designSkill
- rayfin-functionsSkill
- rayfinSkill
- schema-discoverySkill
- visualsSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 10
Read docs/act3.md and instructions/act3.md.
- Very specific: line 12
Keep data/scenario.json frozen and derive the December staffing scenario through scripts/act3/build-staffing-scenario.mjs.
- Very specific: line 14
Use Node.js 24 or later. TypeScript runs through native type stripping.
- Distinctive: line 19
Treat every business record as synthetic and every calculated result as a fixture unless retained tenant evidence proves an observed run.
- Very specific: line 21
Do not print or commit .env, local.settings.json, Azure CLI state, tokens, tenant IDs, account IDs, receipts, screenshots, recordings, or …
- Distinctive: line 23
Do not provision, seed, assign roles, deploy, change Function settings, or run authenticated cloud checks without explicit resource-owner …
- Distinctive: line 26
Never weaken token validation, role checks, source hashes, SQL parameterization, create-once memory semantics, idempotency, or …
- Very specific: line 28
Never overwrite the V3 Cosmos source or reset an approved case.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
Repository instructions for coding agents
This repository contains the full BRK390 session. The publication responsibility
covered here is the Act 3 demo under instructions/act3.md, docs/act3.md,
infra/act3/, scripts/act3/, src/act3/, and the directly related tests and
SQL runtime file.
Start here
- Read
docs/act3.mdandinstructions/act3.md. - Read
.github/skills/caldova-demo/SKILL.md. - Keep
data/scenario.jsonfrozen and derive the December staffing scenario throughscripts/act3/build-staffing-scenario.mjs. - Use Node.js 24 or later. TypeScript runs through native type stripping; do not add a TypeScript compilation step.
Safety boundary
- Treat every business record as synthetic and every calculated result as a fixture unless retained tenant evidence proves an observed run.
- Do not print or commit
.env,local.settings.json, Azure CLI state, tokens, tenant IDs, account IDs, receipts, screenshots, recordings, or build output. - Do not provision, seed, assign roles, deploy, change Function settings, or run authenticated cloud checks without explicit resource-owner authorization for the exact target and command.
- Never weaken token validation, role checks, source hashes, SQL parameterization, create-once memory semantics, idempotency, or uncertain-write handling.
- Never overwrite the V3 Cosmos source or reset an approved case. Create a new
SESSION-orREHEARSAL-case for another run.
Local completion gate
Run:
npm ci
npm run demo:prepare
npm run test:browser
npm run security:publicationThe deployment package is written to build/act3-deploy. Azure deployment and
post-deployment preflight are separate owner-run steps.
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.