CONVERSATIONAL-AGENTS PUB_DATE: 2026.06.16

STOP UPGRADING THE MODEL: ADD RELATIONSHIPS AND STATE INSTEAD

Two new posts argue that explicit relationships and state often beat bigger models for recommendations and AI companions. A Hurix piece makes the case that kno...

Stop Upgrading the Model: Add Relationships and State Instead

Two new posts argue that explicit relationships and state often beat bigger models for recommendations and AI companions.

A Hurix piece makes the case that knowledge graphs outperform vector-only search for learning recommendations by encoding prerequisites and concept links, not just proximity in embedding space Hurix. That shift turns a pile of content into a map of concepts, which changes how paths, gaps, and remediation are handled.

A dev.to writeup shows a cheaper model with a product-layer relationship architecture behaved more like a person than a stronger model without state or boundaries DEV. The signal: model strength helps, but structure, memory, and pacing rules often matter more.

[ WHY_IT_MATTERS ]
01.

Upgrading architecture (graphs, state, boundaries) may yield bigger gains than upgrading the model tier.

02.

Better structure reduces drift, backtracking, and unsafe responses without expensive fine-tuning.

[ WHAT_TO_TEST ]
  • terminal

    A/B: vector-only recommender vs. a small knowledge graph of skills and prerequisites; measure backtracks, completion rate, and dwell time.

  • terminal

    Companion agent: add a finite-state relationship model with boundaries and cooldowns; compare refusal rates and session quality vs. a stronger stateless model.

[ BROWNFIELD_PERSPECTIVE ]

Legacy codebase integration strategies...

  • 01.

    Add a sidecar graph over existing content and events; start by extracting entities, prerequisites, and outcome edges from logs.

  • 02.

    Introduce a lightweight state store for agents (relationship stage, boundaries, last escalations) before touching model configs.

[ GREENFIELD_PERSPECTIVE ]

Fresh architecture paradigms...

  • 01.

    Design a domain graph first-class: entities, prerequisite edges, and progression policies alongside embeddings.

  • 02.

    Separate long-term user state from chat context; route policies through a rules layer before LLM calls.

Enjoying_this_story?

Get daily CONVERSATIONAL-AGENTS + SDLC updates.

  • Practical tactics you can ship tomorrow
  • Tooling, workflows, and architecture notes
  • One short email each weekday

FREE_FOREVER. TERMINATE_ANYTIME. View an example issue.

GET_DAILY_EMAIL
AI + SDLC // 5 MIN DAILY