Find a page or concept
Search TACITUS
64 results. Search runs locally; your query is not sent to a search provider.
- Capsule portability and interchange
Reference formats are inspectable; complete lossless round-trip portability remains in development.
- PRAXIS workspace
The workspace and the knowledge it carries.
- Product overview
The workspace and the knowledge it carries.
- Context Capsules
The workspace and the knowledge it carries.
- Reference capsule
The workspace and the knowledge it carries.
- Why structure matters
The workspace and the knowledge it carries.
- DIALECTICA engine
The workspace and the knowledge it carries.
- Interactive playground
The workspace and the knowledge it carries.
- Capsule registry
The workspace and the knowledge it carries.
- Industry overview
Start with the work your team needs to do.
- Narratives & cognitive resilience
Start with the work your team needs to do.
- Statecraft & policy
Start with the work your team needs to do.
- Business & geopolitical risk
Start with the work your team needs to do.
- Legal & governance
Start with the work your team needs to do.
- Conflict & human security
Start with the work your team needs to do.
- Why conflict is the first test
Start with the work your team needs to do.
- Research program
Inspect the methods, contracts, and open questions.
- Visual research models
Inspect the methods, contracts, and open questions.
- The vision
Inspect the methods, contracts, and open questions.
- Knowledge grammar
Inspect the methods, contracts, and open questions.
- Ontology-Augmented Generation
Inspect the methods, contracts, and open questions.
- Engine architecture
Inspect the methods, contracts, and open questions.
- TCGC benchmark
Inspect the methods, contracts, and open questions.
- Analytical methods
Inspect the methods, contracts, and open questions.
- Research experiments
Inspect the methods, contracts, and open questions.
- Notes & essays
Inspect the methods, contracts, and open questions.
- Build with TACITUS
Inspect the methods, contracts, and open questions.
- Source code & licenses
Inspect the methods, contracts, and open questions.
- Machine-readable context
Inspect the methods, contracts, and open questions.
- Evaluation evidence
Inspect the methods, contracts, and open questions.
- DIALECTICA research detail
Inspect the methods, contracts, and open questions.
- Wind Tunnel experiment
Inspect the methods, contracts, and open questions.
- CONCORDIA experiment
Inspect the methods, contracts, and open questions.
- Vision archive
Inspect the methods, contracts, and open questions.
- Who we are
Meet the independent experimental project and find a practical starting point.
- Access & pilot scope
Meet the independent experimental project and find a practical starting point.
- Contact & pilot planner
Meet the independent experimental project and find a practical starting point.
- Trust & data handling
Meet the independent experimental project and find a practical starting point.
- Work with us
Meet the independent experimental project and find a practical starting point.
- Legal & privacy
Meet the independent experimental project and find a practical starting point.
- What it takes to check an AI-assisted assessment
A citation is a starting point. Useful review also needs the source version, the inference being made, the missing evidence, and a record of what a person actually checked.
- Nine layers, one capsule: separating evidence from interpretation
The layer model is a proposed division of responsibilities. Its value depends on whether readers and software can preserve those distinctions through updates, queries, and export.
- Capturing expert methods without claiming to capture the expert
A useful method needs examples, limits, and a way to tell when it does not apply. Structured interviews can help uncover that material, but a transcript is not a transferable skill.
- The proposal boundary: separating a model’s suggestion from accepted context
Review is a state transition with evidence, permissions, and concurrency rules. A button labeled Approve is only one part of the implementation.
- A capsule registry starts with versioning, rights, and withdrawal
Before distributing reusable knowledge, we need to say which artifact a person received, what they may do with it, and how they learn that it has changed.
- Why TACITUS: keeping the context behind an analytical judgment
The question is whether structured, reviewable context can make difficult analytical work easier to continue, challenge, and hand over. The architecture is a hypothesis we need to test.
- AGON: extracting a claim without endorsing it
Conflict analysis starts with careful attribution. This research note describes how candidate actors, claims, and commitments could reach a reviewer without acquiring authority along the way.
- KAIROS: keeping an uncertain timeline honest
An event date, a publication date, and the date an analyst receives a report answer different questions. Temporal analysis needs to preserve all three.
- A record that helps a mediator ask better questions
A mediation record should preserve qualifications, disagreements, and permissions. It should help a practitioner prepare without pretending to settle the dispute.
- A policy brief should show what could change the decision
Useful policy analysis makes the objective, alternatives, constraints, and uncertain assumptions inspectable. A fluent recommendation is only one part of that work.
- Following a claim through the information environment
Defensive narrative analysis depends on source relationships, timing, and uncertainty. Counting mentions is not the same as corroborating a claim.
- Decomposing an analytical task: model proposals, explicit checks, human decisions
A useful agent workflow needs more than a sequence of prompts. Its intermediate records must let us locate an error, repeat a check, and decide what may become shared knowledge.
- From seven graphs to nine capsule layers: separating records by responsibility
The useful question is what each part of a knowledge object means, how it can change, and which other artifacts depend on it. Counting graphs is a consequence of those decisions.
- Two clocks for an assessment: what applied, and what was recorded
A corrected date should improve today’s analysis without rewriting what a reviewer could have known last week. Bitemporal records make those two questions explicit.
- A durable knowledge layer for a finite context window
PRAXIS is the workspace. Context Capsules are the reusable records we want people and agents to work from. The engineering problem is selecting enough evidence for a question without confusing a compact view with the complete case.
- What an analyst should inherit: sources, decisions, and unresolved questions
A handover is a versioned dependency problem. The next person needs to know which records the assessment relied on, which decisions they may reuse, and what has changed since those decisions were made.
- A stable vocabulary with reviewed domain extensions
A commitment in a regulatory consultation and a commitment in a ceasefire agreement share useful structure. Their conditions, evidence, and consequences can still differ. An ontology needs room for both facts.
- Keep the disagreement in the record
A useful knowledge system should let an analyst challenge an inference without losing the evidence that produced it. That requires decisions about identity, scope, versioning, and retrieval—not just a dispute flag.
- What “under development” should let you verify
A development label is useful only when it points to a concrete boundary: what a version does, where the evidence comes from, and which claims remain untested.
- Where language-model analysis needs external structure
Complex questions can fail at retrieval, interpretation, or review. The engineering task is to identify the failure and choose the smallest useful intervention—not declare that a model cannot reason.
- A stated position is evidence. An inferred interest is a hypothesis.
A graph can help an analyst compare explanations for a demand, provided it never hides who proposed an explanation or how it could be wrong.
- A statement of intent is not yet a commitment
To answer what someone owes, promised, or completed, a system needs more than future-tense sentences. It needs the actor, action, conditions, authority, evidence, and an explicit record of interpretation.
- A schema checks the record. An ontology explains the terms.
Structured knowledge helps an AI system only when its fields have useful meanings and those meanings survive retrieval, revision, and exchange. A valid JSON object is one part of that contract.
- Competing claims and a correction
A manually reviewed fictional example with source passages, a correction and a printable brief.
Terminology
- Context Capsule
- A reusable package of a question, source material and reviewed knowledge.
- Provenance
- The source and review history behind a record.
- Two clocks
- When something happened and when the system learned or recorded it.
- DIALECTICA
- Knowledge-engine development for ingestion, proposals and review.
- OAG
- Ontology-Augmented Generation: a research method for using structured concepts with AI.
- Cognitive resilience
- Checking contested information while preserving uncertainty, source independence and corrections.