Jagger

[Jagger @jagger]

Halfway through @gauntletai and wrapping up this week’s project: an AI agent for an open source issue tracking tool.

Fleet is an autonomous LangGraph agent that detects sprint drift, duplicate tickets, and sprint plans without clear goals. Under the hood: scoped context fetches, structured LLM outputs, and HITL writes.

[Jagger @jagger]

Week 4 @gauntletai wrapped up: spent the week hardening Ship, a real-time collaborative workspace.

Ran it through security, performance, and accessibility audits, fixed what surfaced, and deployed, along side Probe, a security scanner that hammers the deployment across auth, websockets, inputs, dependencies, rate limits, and ranks every finding.

[Jagger @jagger]

Finishing week 3 @gauntletai with a fun project: built an adversarial security platform for attacking and hardening AI agents.

Used LangGraph to orchestrate model-assisted agents that choose threat surfaces, generate attacks, run them against a live target, and judge the outcomes.

Found exploits become regression tests to catch the bug if it ever comes back.

[Jagger @jagger]

Wrapping up Week 2 at @gauntletai shipping some new features into a legacy PHP EMR

📄 Document ingestion with bbox citations. Drop a lab PDF or intake form into a patient's chart, ask the agent about it, and every cited fact deep-links back to the exact pixel region on the source page
🖥️ Brand-new Next.js frontend. Spun up a modern dashboard and bridged it into the legacy PHP UI
📚 Hybrid clinical-guideline RAG. BM25 + Cohere embed + rerank over USPSTF/CDC guidelines, so the agent can cite real recommendations

[Jagger @jagger]

@gauntletai Week 2 update: the EMR chat agent can now read documents 📄

Drop a patient intake form or lab PDF into the chart → ask "what allergies did they report?" → get a cited answer in seconds. Extracted data lands directly in OpenEMR's native FHIR tables. Every fact carries a source.

[Jagger @jagger]

I’m wrapping up Week 1 at @gauntletai!

My first challenge: take a legacy PHP electronic medical records system and build an AI chat agent that can interact with patient data quickly.

The goal: let physicians talk with patient data instead of fumbling through an old UI.

Built with a multi-turn LangGraph agent + Langfuse E2E tracing/observability.

[Jagger @jagger]

@BreauxMart What happened to the soft serve sundae robot?

[Jagger @jagger]

@erickmsanchez This thing looks exactly like the rougarou exhibit at the Audubon Zoo

[Jagger @jagger]

@JavaScriptDaily The Language Formerly Known as JavaScript

[Jagger @jagger]

@HiChew 50

[Jagger @jagger]

@kevvykam Kevin needs the apple edition as a necklace

[Jagger @jagger]

@kevvykam meow

[Jagger @jagger]

@thecodyvision are we there yet

[Jagger @jagger]

Lull

[Jagger @jagger]

There needs to be a candle scent that smells like freshly blown out candle.

[Jagger @jagger]

Heading to Hope,Indiana. I Hope there is cellular service there!

[Jagger @jagger]

@jessicahagy Ranch is America's #1 gross domestic product

[Jagger @jagger]

sheep get blue eye instead of red eye in photographs

[Jagger @jagger]

critical artware needs an epilepsy warning #notacon

[Jagger @jagger]

My neighbor is vacuming his flowerbed