The guess never becomes a fact - provenance-governed, model-free memory for LLMs
Picture: Web Directions

Conference In 6 weeks

December
Monday
to Tue 8 December 2026 · Sydney time

The guess never becomes a fact provenance-governed, model-free memory for LLMs

Where
AI Engineering room 488 George Street, 2000, Sydney
Host
Web Directions
Entry
Not stated
Sign-up
On the host's page
Open on webdirections.org

All Sydney events

You sign up with the host. foundercal only links to it.

Who you meetThe people on the listing, and what the host tells us about the room.

  • Jade Xin Speaker
Investors Not stated The listing does not say
The format Talks and halls Conference
Sign-up On the host's page Price not stated

AboutIn the host's words.

Speakers: Jade Xin (TensorPRO)

Track: AI Engineering

Long context solves within-session coherence, not cross-session persistence. Once an assistant starts storing memories, a quieter failure appears: its own inferences can be written back, retrieved in later sessions, and presented as user facts. Hallucinations then compound over time. We encountered this while building EDN, TensorPRO's external memory middleware. Our response was intentionally less "smart": make provenance structural, and keep generative models out of the retrieval path. Every record carries one of seven provenance classes, including user-stated, document-verified, and AI-generated. A single write chokepoint enforces those labels. At session start, EDN assembles a provenance-gated Session Initialization Package (SIP) using cosine-similarity retrieval. AI-generated records cannot enter factual sections; if one crosses that boundary, the context builder fails loudly. On LongMemEval-S (sealed evaluation, three runs, GPT-4o judge), this design increased answer accuracy from 45.5% with full-history context to 85.4%, while using 9.7× fewer input tokens. SIP assembly p95 was 30–35 ms. Ablations were equally instructive: storing complete turn pairs (round-level records) was the single largest gain, at +22.5 points, while diversity re-ranking (MMR) added no significant gain, so we removed it from the read path. Those results changed what we optimised: not ever more sophisticated retrieval, but governance over what is allowed to become memory.

This talk walks through the failure mode, architecture, evaluation, and trade-offs, including what we would change next. Attendees will leave with a practical framework for deciding when provenance over prediction and determinism over "smart" retrieval are worth the rigidity, and when a probabilistic pipeline is the better engineering choice.

https://data.webdirections.org/ai-engineer-sydney/sessions.json#672b2bfb-1045-4f51-9a27-88693840dff9

Full text on webdirections.org .

Where

AI Engineering room

488 George Street, 2000, Sydney

Open in Maps ↗

Same week in Sydney All 139 events

Dec
to 5 Dec
Hackathon

AI Engineer Hackathon

Founders pitch

Web Directions Free
Dec
to 13 Dec
Conference

AI Week

Web Directions
Dec
to 12 Dec
Conference

NeurIPS 2026

One of the year's big ones

NeurIPS Foundation
Dec
to 8 Dec
Meetup

Lessons from Economics for the Human / Agent Software Workforce

Leadership room
Web Directions
Dec
to 8 Dec
Meetup

Ontologies

AI Engineering room
Web Directions
Dec
to 8 Dec
Meetup

Shipping together in an AI native team

Software Engineering room
Web Directions
Dec
to 8 Dec
Meetup

Dependency hell is back. This time it's your agent's config.

Software Engineering room
Web Directions
Dec
to 8 Dec
Meetup

Your website is a terrible API

AI Engineering room
Web Directions
Dec
to 8 Dec
Meetup

Sovereignty Is an Inference Problem

Leadership room
Web Directions
Dec
to 8 Dec
Meetup

My Agents broke APIs

AI Engineering room
Web Directions
Open on webdirections.org Mon 7 Dec ↗