# AI Work Accountability

> My AI-work portfolio: engineering projects, experiments and field notes, with the decisions and evidence behind them.

Author: ayobamih. This is a personal portfolio. Consult each page for scope and limitations.

## Content
- [OpsTruth](https://aiworkaccountability.com/work/opstruth/): Read-only operational checks that make the evidence and gaps in AI-assisted engineering visible.
- [When the payment succeeds and the agent crashes](https://aiworkaccountability.com/work/pi-stripe-crash-lab/): A fault-injection experiment across the boundary between a durable agent and a real Stripe test payment.
- [What counts as evidence that AI work is done?](https://aiworkaccountability.com/writing/checking-ai-work/): A practical record for connecting a request, an action and an observable outcome.
- [Why I kept the failed result](https://aiworkaccountability.com/writing/keeping-the-failed-result/): A failed assertion can be useful evidence. Removing it would have made this experiment harder to understand.
- [The payment succeeded. The agent crashed.](https://aiworkaccountability.com/writing/payment-succeeded-agent-crashed/): What should recovery do? A real Stripe test-mode experiment, its failed assertion, and the limits of the evidence.

## Alternate formats
- [Catalogue](https://aiworkaccountability.com/content.json): JSON entries with Markdown links and project relationships.
- [RSS](https://aiworkaccountability.com/feed.xml)
- [JSON Feed](https://aiworkaccountability.com/feed.json)
- [Evidence policy](https://aiworkaccountability.com/standards/)

This convenience file is not a search-engine submission or an indexing guarantee.