Build archive

Building Log

Notes, benchmarks, and decisions from Paolo's development.

Last updated September 2, 2026

Competitive field

Approach Differentiator Limitation
Paolo Cognitive profiling via AI conversations 10-dimension fingerprint, taste model, org knowledge layer Requires AI conversations (not passive)
Supermemory Universal memory API, 12-way LLM ensemble 98.6% on their benchmark, open source No cognitive profiling, expensive per-query
Littlebird Desktop screenreading ($11M raise) Sees everything across all apps Desktop only, privacy concerns, no profiling
claude-subconscious Background CC agent (Letta/MemGPT) Agentic — reads code, whispers guidance CC only, coding only
Mem0 Memory API for LLM apps Simple API, broad integrations No profiling, no org layer

Everyone in this space is building memory as storage: save what happened, retrieve it later. We're building memory as understanding: learn how someone thinks, what they prefer, how they make decisions. The moat isn't the data you store, it's the model of the person you build from it.

The Cognitive Fingerprint

Paolo builds a 10-dimension Bayesian profile from natural conversation. No quizzes, no onboarding flows. The profile emerges from how you interact with AI.

Abstraction Level
Concrete examples vs high-level frameworks
Autonomy Preference
Guided step-by-step vs independent execution
Decision Speed
Deliberate analysis vs fast intuition
Information Density
Brief summaries vs thorough detail
Reasoning Direction
Bottom-up evidence vs top-down frameworks
Structure Preference
Freeform flow vs organized systems
Conflict Response
Diplomatic harmony vs direct confrontation
Feedback Style
Gentle suggestions vs blunt critique
Completion Style
Ship fast and iterate vs perfect then release
Collaboration Mode
Solo deep work vs team brainstorming

Benchmarks

95.7%

PaoloBench

Cognitive memory accuracy across 7 categories. Tests what matters for a personal memory layer: preferences, decisions, patterns, temporal reasoning, cognitive profile, entity knowledge.

+3.65

MemoryDelta

Personalization lift in blind A/B test. Memory wins 70% of comparisons. The question: does memory make the response actually better for this specific person?

2.0s

Snapshot Latency

Full profile + preferences + context. Warm cache: 0.4s. Down from 12s+ before optimization.

Recent Milestones

Next

Paolo CC Plugin

One-click install for Claude Code users. Automatic memory capture, context injection, zero configuration.

Next

Write-Time Expansion

Pre-compute search aliases when storing memories, eliminating the read-path LLM dependency for faster, more resilient retrieval.

Sep 2, 2026

Cosmos Institute grantee

Cosmos Institute grantee, Oxford Philosophy x AI track, for Memory Without Capture, a study of how persistent AI memory affects user autonomy. Read the announcement.

Mar 24, 2026

Agent Memory Layer

Automated agents store and share org knowledge through Paolo's multi-tenant infrastructure. Agents share context with each other and with humans in the same org.

Mar 23, 2026

Claude Code Hooks

Automatic session capture with 0.13s context injection. Tool actions captured in background, session summaries synced on exit. No manual memory calls needed.

Mar 22, 2026

PaoloBench + MemoryDelta

Two novel benchmarks measuring cognitive memory quality and whether memory actually makes AI responses better for a specific person.

Mar 20, 2026

Performance Overhaul

Snapshot latency from 12s to 2s. Circuit breaker for API resilience. Accuracy canary monitors retrieval quality every 6 hours.

Mar 18, 2026

Privacy & Security Audit

63-test E2E suite. Credential scrubbing, raw message stripping, entity sensitivity classification, OAuth hardening.

Mar 14, 2026

Organization Layer

Multi-tenant knowledge sharing with role-based access. Built for The Operator, designed for any team.

Mar 4, 2026

Cognitive Engine v2

10-dimension Bayesian fingerprint from 2,774+ observations.

Founder Thoughts

Mar 25, 2026

Everyone is building AI memory. Almost nobody is measuring whether it works.

This week we built MemoryDelta, a benchmark that asks a question nobody else seems to be asking: does having memory actually make the AI response better for this specific person? Not "can you retrieve fact X" but "did knowing X change the output in a way that mattered?"

The answer: memory wins 70% of blind A/B comparisons, with a +3.65 personalization lift on a 5-point scale. But accuracy only improves by +0.05 without confidence signals. Memory makes AI more personal, not more correct. That's a crucial distinction that shaped how we think about retrieval quality going forward.

Mar 23, 2026

Curated memory vs captured memory

Littlebird raised $11M to build AI that watches your screen. Supermemory has 17K GitHub stars auto-capturing everything. Both are betting that more data equals better understanding.

We're betting the opposite. Paolo stores what the AI chose to remember, not everything it observed. The user is the author of their own memory, not the subject of surveillance. There's something meaningful about the difference between "I told my AI about myself" and "my AI watched everything I did." We think the first one builds trust. The second one might be more complete, but completeness isn't the same as understanding.

Mar 22, 2026

Why we don't win on MemoryBench (and why that's fine)

Supermemory's MemoryBench tests raw transcript retrieval: "what did the user say in conversation 7?" Paolo scores 20% on that benchmark. By design. We deliberately strip raw messages for privacy and store summaries and observations instead.

So we built our own benchmark, PaoloBench, testing what we think actually matters: preference recall, decision tracking, cross-session patterns, cognitive profiling, entity knowledge. We score 95.7%. But we also published our MemoryBench score, because intellectual honesty about what you're bad at matters more than only showing the numbers you like.