Posts by IgorGanapolsky
@IgorGanapolsky
Igor Ganapolsky
Forward Deploy AI Engineer
Posts by IgorGanapolsky
Why AI Coding Agents Need a Feature Flag Firewall: Inside Spotify Confidence MCP + ThumbGate
Spotify's experimentation team just announced "A New Chapter for Confidence" October 14, 2026, launching Confidence Agent, Session Recordings, and official...
Why Your AI Copilot's Thumbs-Down Sucks: From Passive CSAT Black Holes to Pre-Action Firewalls
The Production Failure Youâve Probably Experienced Today
You open your workplace app. On the left side of your screen, your meeting calendar shows:
> F...
Why AI Agent Sandboxes Aren't Firewalls: Moving Beyond Post-Action Observability to In-Line PreToolUse Interdiction
> ThumbGate Engineering Daily | 2026-10-09
> Author: Igor Ganapolsky @IgorGanapolskyhttps://github.com/IgorGanapolsky
> Verified...
Autonomous AI coding agents promise 10x developer leverage. But without runtime execution guardrails, a single failing tool call can send an agent into an exponential token-burning compaction spiral.
The Incident: 301,424,414 Tokens Burned in 24 Hou...
A person should see the calls that change something. Reads can run when a policy already allows that tool and those arguments.
The failure mode
Reviewing every tool call does not scale, and reviewing none of them leaves a coding agent free to write...
A system prompt asks the model to behave. The tool call still goes out when the model ignores that ask.
ThumbGate sits in front of the call. The PreToolUse hook reads the command before it runs and can block it. A thumbs-down on a bad call becomes a...
Test Article
Operational metrics, injection/PII scrubbing, quality evals, and parented spans without heavy vendor SKUs....
Why persistent, structured context — not bigger prompts — is what makes AI coding agents reliable.
What is a "context brain"?
A context brain is a single, persistent, versioned artifact that an AI agent reads before it acts — so it starts every tas...
chevron_left