How Model Evolution Has Reshaped Security AI Agents on H1 Platform
ID: 1c5940bf-da0a-5ddf-a10e-94a1ba9a56a7
STIX ID: report--1c5940bf-da0a-5ddf-a10e-94a1ba9a56a7
Feed Name: HackerOne Blog
This report summarizes HackerOne's 18-month evolution (Mar 2025–Aug 2026) of AI agents for code security: how model-to-task delegation, output-format phases (free-form JSON → structured output → tool-call outputs), invocation stacks, and stricter guardrails changed agent architecture and product workflows (H1 Code, H1 Remediation, H1 Code Security Audit), with lessons on balancing fast/balanced models for breadth and deeper-reasoning models for judgment.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.