01Python · standard library
Runnable reference
Policy knowledge pipeline ↗
Exact sources → semantic layer → bounded capsule → cited draft. Includes an evidence-inspection agent and explicit cloud/local provider adapters.
Tacitus / AI data infrastructure
Policy expertise.
Structured for AI.
Data infrastructure for AI, for better knowledge generation. Built for policy and political analysis.
Inside a policy knowledge pipeline
Drag to rotate · click a point
Capture the exact text.
Keep the passage, source edition and historical wording together.
Historical source · resolution 2254 (2015)
Inspect a record & its source
Text occurrences, published vocabularies and authored mappings are distinct. Recorded AI output remains for review; generation-quality gains need evaluation.
TACITUS APP Invite-only pilotYour policy research desk.Sources. Capsules. Drafts.Open the App ↗
TACITUS CONSULTINGResearch and advisory.Work with our team ↗Make meaning explicit.
Concepts, ontologies, relationships and weighted source records.
Explore the knowledge ↗02 / CapsulesBring the right context.
Task-specific sources, distinctions and expert checks for AI.
Inspect a capsule ↗03 / ArtifactsProduce useful work.
A briefing, comparison, meeting agenda or review note.
Open an artifact ↗Start with the work
What do you need
to produce?
- Research synthesis for a decision
- Bring a question and a source collection. Scope a brief that brings together findings, disagreements and open questions.
- Regulatory & policy evidence tracking
- Keep policy versions, requirements and supporting evidence in a dated register, with gaps and review responsibilities visible.
- Source-preserving briefs
- Prepare a brief whose claims can be checked against source passages, dates and qualifications.
Source access, scope, deliverables and review are agreed per engagement.
Public repositoriesCode, setup and development status+
The public code
Open the implementation.
02TypeScript
Local reference
Context workbench ↗
Source-linked data formats and local inspection utilities. Product workflows are being built separately.
03Rust
Experimental core
DIALECTICA ↗
Explore capsule contracts, typed context and ontology-backed preparation.
Public examples and research code. The App’s core is private. Generation-quality benchmarks remain in development.
Why structure the knowledge?Identity, evidence, conditions and reuse+
Why structure the knowledge?
Keep the distinctions
that change a briefing.
Policy work depends on attribution, changing identities and conditional language. Capture them once as source-linked records, then reuse them across questions and drafts.
Discuss your research needs ↗- Identity
- Which actor is meant? An alias or affiliation does not establish shared authority.
- Evidence
- Which report is original? Repetition does not become independent confirmation.
- Language
- Which dates, limitations or exceptions must stay with the claim?
- Reuse
- Which source and version support the next brief? Retrieve them together.
Start with the work
Where to start with
Policy / Political AI.
A recurring task. A clear output.
Evidence a reviewer can check.
If your team is facing…Start with…
Opening the task guide…
Inspect the selected example
Explore the knowledge
behind a question.
Choose a use case. Inspect the published vocabulary, source passages and task-specific connections.
Opening the knowledge database…
Why this layer?
Open a layer to inspect its purpose.
Published vocabularySource materialTask & assessment
Explore nodes as a list
Saliency and efficiencyKeep decisive evidence; measure the whole cost+
Saliency
Keep the evidence
that changes the answer.
Preserve dates, exceptions, attribution and missing inputs. Select complete evidence before supplementary instructions.
Efficiency
Spend context
on the actual task.
Reuse defined concepts and deduplicate sources. Measure context cost and output quality together.
Research, tests and limits ↗Deterministic means the same records and rules give the same structured result. It does not make political interpretation or model generation deterministic.
Questions and referencesMethods, research and limitations+
Questions worth asking
Why this work matters.
Why prepare policy knowledge before asking AI?
A useful policy answer depends on who said something, which actor they meant, the source version and the conditions attached. A knowledge pipeline captures those relationships once, so each briefing can reuse and inspect them. The intended benefit is less repeated preparation and fewer lost distinctions. Each workflow still needs evaluation.
How can data structures improve saliency?
Saliency means keeping the evidence that changes the conclusion. A task-specific structure can retrieve the relevant actor, clause and exception together, instead of sending an undifferentiated document pile. Models can still miss or misuse that evidence. Lost in the Middle shows that evidence position matters in the tested long-context settings; it does not validate Tacitus.
Where can efficiency come from?
Reusable definitions and source records reduce repeated assembly. Deduplication can avoid spending context on the same evidence twice. Selection can keep unrelated material outside the task. Building and maintaining a graph also costs time and compute, so we measure preparation, retrieval, model usage and review together. Shorter context alone is not success.
How can a brief retain its supporting evidence?
Keep source links, dates and relevant passages alongside each claim. Record which version was used and flag gaps or qualifications for review. This supports source checking; it does not establish that a claim is true or replace the analyst’s judgement.
What has Tacitus actually benchmarked?
We have reproducible checks for evidence retention, context size, source identity and rules. A frozen 24 KB compiler regression now keeps three exact quotations and an artifact that the old version omitted. An earlier 48-response model evaluation had mixed results. We have not established a general improvement in generation quality, inference cost or analyst time.