Tabletop Arc

AI Campaign Continuity: How to Run a Campaign That Remembers Everything

AI campaign continuity is the practice of using a structured canon ledger, evidence-grounded recaps, and a living wiki to keep every TTRPG session connected. Tabletop Arc is the AI memory layer for tabletop campaigns: every fact links to the transcript that proves it.

What is AI campaign continuity?

AI campaign continuity is a practice for keeping long-running TTRPG campaigns coherent across many sessions. A canon ledger stores every NPC, location, and quest as a structured fact. Each session adds a diff with evidence (transcript timestamps) and confidence (HIGH / MEDIUM / LOW). The result is a living wiki that compounds session over session and never loses a thread.

Why does campaign continuity break in long-running TTRPG campaigns?

Most campaigns fail at memory long before they fail at story. The GM forgets which NPC the players liked. A faction motivation drifts between sessions four and seven. A magic item changes hands offscreen and never gets reconciled. By session twelve, half the table is fact-checking the other half — and the canon stops being canon.

Continuity is not about discipline. It is about infrastructure. AI campaign continuity is the practice of treating campaign state as a structured ledger that the GM, players, and (optionally) AI all read from and write to.

What is a canon ledger?

A canon ledger is a structured record of facts about your campaign world. Every NPC, location, faction, item, quest, and event is stored as an entry. Every entry has:

  • A canonical name and short summary
  • A list of evidence segments (transcript timestamps where the fact was established)
  • A confidence level (HIGH, MEDIUM, or LOW)
  • A diff history showing how the fact has changed over sessions

When canon is structured this way, AI tools can do the heavy lifting: extract entities from session transcripts, propose updates to canon, surface the items that need GM review, and produce evidence-grounded recaps that never invent facts.

How does evidence-grounded recap work?

A recap is evidence-grounded when every claim in it can be traced back to a specific transcript moment. Tabletop Arc generates recaps by walking the canon ledger of an episode and grounding each statement in the segments tagged during analysis.

Two consequences fall out of this:

  1. Hallucination is impossible at the recap layer, because the AI is only allowed to reference facts that exist in the ledger.
  2. Corrections are first-class. When a GM notices the recap got something wrong, they can correct the underlying fact and the recap regenerates correctly the next time.

What is dual-track output?

Long-running campaigns need two outputs from every session: GM-private notes (open threads, secrets, "to confirm next session") and player-safe recaps (no spoilers, optionally annotated with entity links). Dual-track output is the standard pattern in Tabletop Arc; the same canon ledger emits both views with different visibility filters.

How do you start?

You do not need to migrate every session at once. Start with the next session: upload the audio, let analysis extract scenes and entities, review the proposed canon updates in the queue, and publish the recap. The first session establishes the canon ledger. Every subsequent session adds a diff. By session four or five you have a wiki that compounds.

Try it yourself — generate a free NPC right now

No sign-up required. Generate NPCs, quests, locations, and more.

Open NPC Generator

Frequently Asked Questions

Is AI campaign continuity the same as note-taking?
No. Note-taking is unstructured prose that only the note-taker can interpret. AI campaign continuity is structured: each fact is a typed entity (NPC, location, faction, etc.) with evidence, confidence, and a diff history that any GM, player, or AI tool can read.
What if my players contradict canon?
Canon evolves. When a player surfaces a fact that contradicts existing canon, the GM can resolve it as a correction (rewriting the canonical entry) or a retcon (adding a new event that changes the world). Both flow through the ledger as first-class diffs.
Do I need to record every session?
No. You can write a manual recap for sessions you did not record. The structured ledger accepts both AI-extracted facts (from transcripts) and manually entered facts (from GM notes), so the wiki keeps growing either way.
How is this different from a campaign management tool?
Most campaign managers are storage. AI campaign continuity is a workflow: facts in, evidence-grounded outputs out, with corrections as first-class events. Tabletop Arc is the AI memory layer — facts persist, propagate, and compound, instead of just being filed.
How does AI campaign continuity help with new players joining mid-campaign?
A living wiki lets new players catch up via player-safe recaps and entity pages. They can read the canonical NPC summaries, the timeline, and the world codex without needing the GM to debrief them in person.
Will AI hallucinate when summarizing my sessions?
Tabletop Arc grounds every output in the canon ledger and the segment-level evidence behind it. The AI is constrained to reference existing facts and quote existing transcript segments. Free-form generation only happens at the proposal stage, where the GM reviews and approves before anything enters canon.
Can players see the canon ledger?
Players see the player-safe view: the public Lore Wall, recap, and timeline. The GM-private layer (open threads, pending reveals, low-confidence rumors) is gated by visibility flags on each entry.
What confidence levels are used?
HIGH (multiple sources or explicit canonical statements), MEDIUM (single confident source or strong inference), LOW (rumor, hearsay, or AI inference flagged for review). Low-confidence facts are surfaced as "to confirm" rather than asserted as canon.

Related Tools

🧙

NPC Generator

Generate detailed, memorable NPCs with personality, motivation, and secrets.

📜

Quest Generator

Build multi-layered quests with hooks, complications, and satisfying twists.

📖

Plot Arc Generator

Generate complete campaign arcs with acts, factions, NPCs, and quest hooks.

Related Articles

The AI Memory Layer for Tabletop Campaigns

An AI memory layer is the persistent, structured record of every fact in your TTRPG campaign — characters, locations, factions, quests, evidence, and confidence — that AI tools can safely read, update, and reference. Tabletop Arc is that memory layer.

Persistent Campaign Memory: Make Your TTRPG Canon Compound Session Over Session

Persistent campaign memory is the structured, evidence-grounded record that turns isolated TTRPG sessions into a coherent, multi-year campaign. Tabletop Arc is the AI memory layer that lets canon compound instead of decaying.

TTRPG Lore Tracking: How to Keep Campaign Canon Coherent for Years

TTRPG lore tracking is the practice of capturing every canonical fact about your tabletop campaign — characters, locations, factions, secrets, and rules — in a structured, evidence-linked record that compounds across sessions. Tabletop Arc is the AI memory layer for tabletop campaigns.

How to Build a Living Campaign Wiki for Your TTRPG (Step-by-Step)

A step-by-step guide to building a living campaign wiki for D&D, Pathfinder, or any TTRPG. Use AI extraction, structured canon, and evidence-grounded entries so the wiki updates itself as you play.

How to Run Long-Term TTRPG Campaign Continuity (1, 2, 3+ Years)

Practical guide to running a TTRPG campaign that holds together for years. Structured canon, evidence-grounded recaps, dual-track outputs, and an AI memory layer that turns every session into compounding canon.

Automatic D&D Recap Tool: Turn Session Audio into Player-Ready Recaps

An automatic D&D recap tool transcribes your session, extracts scenes and entities, and generates evidence-grounded recaps in player-safe and GM-private formats. Tabletop Arc is built for long-running campaign continuity, not just one-shot summaries.

Keep going