The Big Picture
This is a largely autonomous system. It discovers events, monitors its own health, and fixes many of its own bugs — every day, with minimal human intervention. The Observatory exists to give transparency into this process so people can see how an autonomous AI system actually works. This isn't a black box.
How It Works
The whole system, end to end — it runs largely on its own, with a human reviewing only the riskiest changes.
Discovery Pipeline
— runs nightlyOpus reviews recent results and decides what to scrape and search today
Scans a dozen curated sources and the web for Austin AI events
Catches the same event listed on different platforms
AI confirms: real event? In Austin? AI-related?
Tags audience, skill level, and free/paid
Approved events appear on the calendar
Self-Monitoring
— evaluates every runCollects data on scraper health, error rates, source performance, and calendar coverage
The most powerful Claude model reviews everything, assigns a health grade, and identifies issues
Creates search queries, manages sources, and escalates code issues for the repair agent
Self-Healing
— runs daily, 2 hours after discoveryPicks up the highest-priority action item from the monitor
Diagnoses the root cause — fetching the live web page through a supervised relay, since the agent deliberately has no direct internet access
Reads the codebase, understands the bug, and writes a fix
Runs the full test suite, then tests the fix on a draft branch against the real live page — a fix that fails the rehearsal never touches production
Ships proven low-risk fixes to production automatically; flags riskier changes for a human to review first
The Independent Watchdog
A separate watchdog— its own program, running outside this system on its own schedule — independently counts how many Austin AI events exist and compares that to how many the calendar has captured. Because it lives outside the agent, the system can't grade its own homework: if coverage quietly slips, the watchdog is the thing that catches it.
Multi-Model Architecture
Three Claude AI models split the work based on what each task needs — like having a junior analyst, a senior reviewer, and a strategic director on the same team.
Handles 80% of decisions — validation, classification, dedup
Evaluates new sources and extracts event details
The system brain — plans each run and monitors system health
Community Input
Anyone can submit an event the system missed using the “Missing an event?” button on the calendar. The agent scrapes the submitted URL, validates it, and adds it to the calendar — all in the same daily run. It also learns from each submission, adding new sources and search strategies to find similar events in the future.
Where It Goes
Each morning, Claude summarizes the overnight run — what it found, what broke, and what it cost — and emails it to the operator. It's how a human keeps an eye on the system without having to run it.
Every Sunday evening, anyone who's subscribed gets the week ahead in Austin AI events delivered straight to their inbox.
Agent Performance
What the agent is doing autonomously
Events Added (Last 30 Days)
Recent Activity
Under the Hood
How the agent thinks, decides, and sometimes fails
Health Report
Automated self-evaluation of system effectiveness
| Grade | Scraper Health | Sources | Error Rate | Activity |
|---|---|---|---|---|
| A | 80%+ | 4+ contributing | <5% | Events added in last 7d |
| B | 60-79% | 3+ contributing | <10% | Active discovery |
| C | 40-59% | 2-3 contributing | >10% | Some source issues |
| D | <40% | <2 contributing | High | Multiple broken scrapers |
| F | — | — | — | System not running |
Updated 2026-03-29: Grades now measure infrastructure health (what the agent controls), not event count or empty days (which reflect community activity). The agent still actively maximizes calendar coverage as a separate mission.
Human Stewardship
How humans guide the agent's growth
Human Stewardship
How humans guide the agent's growth using Claude Code
Dropped sources were supposed to get a second chance. A source with a real track record was re-checked about 30, 60 and 90 days after it was dropped, then never again, and a source with no record was never re-checked at all. In Austin even that never happened. The re-check only ever looked at the 50 oldest of Austin's 151 dropped sources, none of those 50 qualified, and so Austin had never re-checked a single one. An Austin meetup group was due in September and again in October and was never looked at.
Every dropped source is now retested every 30 days, with no limit on how many times, up to six per run. One passing event is enough to put it back on probation: an upcoming event already on the calendar, or a new one that passes the location check and the AI check. Search and discovery pages, which mostly list events the calendar already has, get no free pass for those and have to find one new event. A few never come back on their own: pages that are gone or keep refusing the scraper, and any source the operator has already ruled on. A source that comes back keeps its record of passed events, and its failure count starts over, so one bad event doesn't drop it again.
This replaces the three re-checks described in August, and the reasoning behind them, that retrying on a schedule would mean checking dead pages forever. Dead pages are now retired on their own, so the monthly look only reaches pages that still answer. Austin's first retests start with the next nightly run after this change.
This agent is developed iteratively with Claude Code. The collaboration is part of the project's identity.