Backtest Your Agent Against Yesterday's Web — Ryan Ahern, Exa
How do you know whether your agent would have made the right call?
Ryan Ahern of Exa shows how to use version-controlled search to see the web exactly as it was on a past date, then backtest an agent's predictions against what actually happened. The hands-on example predicts company acquisitions from signals like leadership turnover, then tunes the system without leaking future information. Chapters: - 00:00 Why search matters for agents - 04:15 Exa's search benchmark - 06:17 Versioning the whole web - 10:34 Avoiding look-ahead bias - 14:43 Backtesting and tuning a predictor - 18:49 Hands-on: predicting acquisitions - 22:54 Results and overfitting Ryan Ahern — https://exa.ai Join us in SF for the second annual AIE CODE summit: https://aie.codes our last flagship summit of 2026. Applications live now!
The text is the source's own description of its publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago