Fab Isnard

Fab Isnard

Sales Development

About

I build and scale the GTM operating systems that turn partner, product and prospecting signals into predictable enterprise pipeline and revenue. I have done it at Cloudflare, AWS and Salesforce over 18+ years in go-to-market, 16 of them in APAC, leading Sales Development, Inside Sales and Partner organisations.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Forums

•

15h ago

How to use AI agents to catch edge-case bugs before code review

Relying solely on manual unit tests often misses weird input combinations that users somehow always find in production. Last month, a timezone offset bug slipped past our standard test suite and broke scheduled notifications for overseas accounts.

I configured an autonomous AI agent in our CI pipeline to read every new pull request diff and generate adversarial test inputs. Instead of checking happy paths, the agent specifically targets null values, boundary dates, and malformed payloads.

It caught four subtle race conditions during its first week of operation before any human reviewer even opened the pull requests. Code reviews now focus on architecture rather than hunting down missing null checks.

  • Instruct your test agent to focus on boundary conditions and unexpected data types.

  • Run generated edge-case tests in an isolated sandbox environment on every commit.

AI more than tripled the code. Releases rose 30%. Usage didn't move. Where's your bottleneck now?

A new study puts numbers on something a lot of us feel: writing code got cheap, and almost nothing after it got any faster. I'd like to hear where the slowdown sits for your team.

I've been reading "Writing Code vs. Shipping Code," an NBER working paper by Mert Demirer (MIT Sloan), Leon Musolff (University of Pennsylvania) and Liyuan Yang. It follows GitHub developers before and after they adopted three generations of AI coding tools: autocomplete, interactive agents that edit alongside you, and autonomous agents that work on their own.

The headline from the revised version on NBER's site (September 2026): cumulative increases in commits of about 30%, 180% and 240% across those three generations. Then the gains shrink at every step down the line. The 240% in commits becomes about 80% more projects and about 30% more actual releases. An earlier May draft had different commit numbers, but the same shape and the same roughly 30% on releases.

The part that stuck with me is the app stores. The authors looked at four marketplaces (Apple's App Store, Google Play, the Chrome Web Store and SourceForge) and found a sharp rise in new apps, but no increase in total usage. More things shipped. People didn't use more things.

View more