by iqentity | Apr 9, 2024 | Development, Tessera
Tessera will never make an API call. Not to OpenAI. Not to Anthropic. Not to any cloud service. The entire system, language model, retrieval infrastructure, knowledge graph, and agentic layer, runs locally on hardware I control. This is not paranoia. This is...
by iqentity | Apr 6, 2024 | Development, Tessera
Retrieval is everything. If Tessera cannot find the right precedent for a new situation, nothing else matters. I spent this month building a hybrid retrieval system that prevents the failure modes I have seen in every other approach. Why Single-Method Retrieval Fails...
by iqentity | Apr 4, 2024 | Development, Tessera
The graph is taking shape. Two months of ingested data, and the lattice structure is emerging naturally from the decision extraction process. The patterns are real. The Node Structure Each decision node contains: the decision itself (what was chosen), the signals that...
by iqentity | Apr 2, 2024 | Development, Tessera
The ingestion pipeline is operational. Three weeks of building, testing, and refining against real data from my corpus. The results are better than expected, but the challenges were different from what I anticipated. Pipeline Architecture Stage 1: Format...
by iqentity | Mar 27, 2024 | Development, Tessera
Something emerged from the early extraction runs that validates the entire approach. The data confirms what the psychological assessments suggested: the same decision engine operates across all domains. What the Data Shows When I analyze how I handled legal risk...
by iqentity | Mar 22, 2024 | Development, Tessera
I spent the last two weeks building the extraction pipeline, and the design philosophy is paying off. Every artifact in my corpus is treated as evidence, not truth. The distinction matters. How Extraction Works An email is not an opinion to be stored. It is decision...
