Research-stage · Fine-tuning an EI model
Find where AI loses the human context.
Affective is fine-tuning an EI model that chooses the right conversational decision, with person state as an external, person-editable memory component. Transcript evaluations of how agents mishandle people are the first state add-on.
Trace the moment
Find the exact turn where context was lost or a response missed a change in need.
Inspect the evidence
Record the observed signal, comparator, and uncertainty instead of assigning a hidden emotion score.
Test the decision
Ask whether structured state adds value beyond a strong transcript or summary baseline.

The first commercial question
Before an agent remembers people, test where it fails them.
On the v2 sequence, the API's first offer is the fine-tuned EI model. The first state add-on is evaluation of existing agent transcripts, the part we can discuss in detail today. The report format is designed to show a specific failing turn, the method used to identify it, an appropriate comparator, and what remains uncertain. A production Observe or Runtime service is a later gate.
01 / INPUT
An authorized conversation
Data rights and privacy terms come before any transcript review.
02 / REVIEW
Inspectable mishandles
Missed escalation, lost state after a topic shift, and inappropriate agreement are initial evaluation targets.
03 / OUTPUT
Evidence, not a magic score
The planned deliverable is an auditable trace with limits, not an unverified emotional diagnosis.
Where this is headed
Emotionally intelligent AI, in five gated stages.
The long-term product is AI that keeps track of the person it is talking to, reached through an API and the Affective platform. Nothing is live yet. Each stage opens only if the evidence supports it.
01
EI model
Research nowA fine-tuned open-weight chat model that infers what a person feels, how strongly, and why, chooses a response strategy, and replies truthfully. Served through an OpenAI-compatible API with strategy and appraisal readouts.
02
Memory
After the model validatesPersistent, person-editable memory per end user, used by the model. The person can see and delete it.
03
State add-ons
Each behind its own gateEvals (mishandle suites), Observe (production scoring), Runtime (state for any model), and Scenario Data, sold on the same API.
04
Voice
Separate track, own gatesAffective Voice: our own realistic voice models. V1 half-cascade first; speech-to-speech only if it measurably wins.
05
Foundation model
Series A planThe from-scratch EI-native foundation model behind the same endpoints.
Evidence, with its limits
A result earns a claim only at its own gate. We report synthetic, development, and real-person evidence separately, including negative results.
Snapshot: October 25, 2026. Read the evidence map
Research track: Voice
Speech is evidence. Core decides.
Affective Voice is a separate research track building the V0 cascade toward a V1 half-cascade, with an offline path for transcript and acoustic observations, plus an initial TTS adapter. Speech signals carry quality, uncertainty, provenance, and consent limits. They are not a direct reading of someone’s private emotion.
Read the voice researchCurrent boundary
Offline observation is implemented.
Offline onlyValidated production speech-emotion inference, Core integration, live streaming, and release remain future gates.
Join the team
Chief Marketing Officer (CMO)
We are looking for a marketing leader who can make a rigorous, research-stage story legible to AI teams without outrunning the evidence.
