FidetoLabs build logs
We share the journey of building data tools and studies at FidetoLabs.
Latest posts
3 min read
Why an AI Agent Needs a Deterministic Interface on Substack
Building a Human Interface for an Agent-Operated System
3 min read
Rethinking Data Lineage and Job Scheduling on Substack
How I redesigned Qanat’s data ingestion, execution tracking, and project configuration.
6 min read
Where Should User Data Live? on Substack
An Architectural Decision Between a Data Platform and an AI Research Application
11 min read
When AI Agents Control the Wallet: The Next Great Shift in Commerce on Substack
The internet was built for humans to search, compare, and buy. The next version of commerce may be built for machines to decide and transact.
4 min read
Your Agent Is Reading Files You Never Told It About on Substack
Why giving your trading LLM file system tools is a terrible idea, and how to fix it with an API.
7 min read
How Claude Code’s Subagents Keep the Main Context Clean on Substack
Why the useful thing a subagent does is not “run in parallel” but “do the noisy work somewhere else and hand back only the summary.”
6 min read
How Manus Keeps Tools Stable by Masking Logits Instead of Swapping Them on Substack
Why a growing tool catalog breaks long agent loops — and how Manus constrains the next action without rewriting the tool list.
6 min read
What Higgsfield Supercomputer’s Orchestrator Actually Does on Substack
How one brief gets split into steps, routed to different models, and run without you choosing Claude, Seedance, or Kling each time.