WHY CONFLICT · WHY NOW
Drop a WhatsApp screenshot, a transcript, a policy brief , TACITUS builds the picture, with time. Primitives, contradictions, trajectory. The human decides; the engine supplies the foundation.
Problem
Parties see different pictures of the same situation.
Response
One shared, typed, sourceable map of the dispute, as it evolves.
Boundary
We do not decide who is right. Humans still do.
INTERACTIVE · 5-DAY DISPUTE, UNFOLDING
Paste a transcript, a Teams thread, a chat export, or case notes. The engine builds the case as new artefacts arrive and keeps every primitive timestamped and cited. Advance the conversation below to watch the graph form, the issues flag, and the trajectory emerge.
So we're agreed: you own the Q4 launch deck content, I handle design. Lock it in by Thursday?
EXTRACTED PRIMITIVES · 3
ISSUES FLAGGED · 0
No issues yet. Issues surface as contradictions, drift, or escalation vectors appear.
ONE CASE · FLAGSHIP + ENGINE + ADJACENT
The Sam ↔ Alex thread is the same artefact for everyone. PRAXIS is where the analysis lives. DIALECTICA is what makes it reason. CONCORDIA and Wind Tunnel are side projects on the same backbone.
PRAXIS
Flagship · The flagship workbench
Open a case file. Ingest the Sam ↔ Alex thread, the prior history, the Jenkins-pitch context. Output a cited briefing for the manager — and let the manager argue with it before signing off.
/product/praxisDIALECTICA
Engine · The engine underneath
The reason every primitive in the case is typed, time-ordered, and traceable. Not a product — the credibility layer PRAXIS runs on.
/product/dialecticaCONCORDIA
Side project · When the room actually meets
When HR steps in for the live Sam + Alex + Rachel session, CONCORDIA binds every utterance to a primitive and flags commitment drift as it happens. Side project on the same engine.
/product/concordiaWind Tunnel
Side project · Stress-test before you escalate
Before the team sends a public statement, test three drafts against synthetic publics and behavioral segments. Pick the one least likely to entrench the dispute. Side project on the same engine.
/product/windtunnelWHAT YOU ARE USING TODAY
Three ways to hold a dispute in memory. Only one of them is structure.
Post-its & inbox
Where most dispute memory lives today
Generic LLM (ChatGPT, etc.)
Fluent paragraph, no structure
TACITUS
Typed graph, cited, time-ordered
WHO IT IS FOR
Same primitives, different stakes. Each role gets the same typed graph , and a product tuned to their cadence.
Policy desks & mission staff
Briefings, SITREPs, multi-actor case files
Diplomats & Track II teams
Process memory, commitments, narrative drift
Mediators & ombuds
Live sessions, commitment tracking
Peacebuilding & humanitarian teams
Evolving commitments, contested events
Communications & crisis leads
Message stress-testing, polarization risk
Risk, compliance & legal counsel
Whistleblower reviews, ADR mapping
Conflict researchers & think-tanks
Archive-scale, cited synthesis
THE ARGUMENT, IN THREE PARAGRAPHS
We are not trying to end conflict. It is the default state of any system with more than one agent and more than one goal. What we try to do is more modest and more concrete: show every party the same map.
Decades of research across law, political science, organisational behaviour, mediation theory, and moral psychology converge on a single finding , disputes have structure. Actors, claims, interests, commitments, events, narratives. That structure is learnable, and until now it has been invisible.
Current AI tools miss this entirely. Ask a generic LLM "who broke which commitment, when, and under what pressure?" and you get a confident hallucination. Dialectica, the neurosymbolic engine underneath TACITUS, closes that gap , primitives extracted against the ACO, stored in a typed graph, reasoned over deterministically.
We do not make peace. Peace is a human choice. We make disagreement legible enough that humans can make it.
THE GRAMMAR · ACO
Who participates
Individuals, teams, institutions, states, coalitions: any agent with goals and agency in the dispute.
What is asserted
Factual, evaluative, or normative statements a party makes. The surface of the disagreement.
What lies beneath
Underlying needs and motivations. Fisher-Ury: what the party actually needs, versus the position they state.
What limits outcomes
Rules, regulations, norms, hard facts. The structural bounds on possible resolution.
What holds the power
Resources and dependencies that give a party the ability to act, withhold, or influence.
What was agreed
Promises, contracts, pledges, ceasefires. The graph-layer distinction between asserted and agreed.
What happened when
Time-stamped, provenance-carrying occurrences. The temporal DAG underneath every case.
How it is framed
The story each party tells about the dispute. Captures framing, re-framing, and narrative drift over time.