AIVAX / Blog

Notes from the operating layer.

Field notes on AI infrastructure, retrieval, model operations and the systems that keep every request visible.

12 published field notes

Latest blog posts

  1. A weathered wall of card-catalog drawers with blank brass label plates, one drawer half-open with a slipped card tied by a single red thread to a small brass desk lamp

    AIVAX Labs

    Persistent memory is a write path, not a notebook

    An agent that writes its own memory gains a second input channel that outlives the session. Recent poisoning research shows why that channel needs ownership, expiry, and review — and how AIVAX scopes it.

    Read post
  2. A stone sluice gate with three channels meters a river of record-cards into calm terraced basins while a gatekeeper works a lever

    AIVAX Labs

    Batch is an admission-control problem, not a queue

    Bulk AI work fails at the boundary between the queue and the provider: rate limits, balance, validation, and overload. AIVAX Batch answers with bounded admission, per-item validation, and failure-shaped retries.

    Read post
  3. Terraced night gardens crossed by thin diagram paths with node dots, one ember-red path veering away past a small stone watchtower

    AIVAX Labs

    From test to monitor: the judge trajectory as a production signal

    Agentic Tests already scores every turn of a simulated conversation. Applied to real production traffic, the same trajectory signal — score, at-risk state, persistent loss — tells you when a live conversation is drifting before the user gives up.

    Read post
  4. Blue request cards, each carrying a yellow state token, travel independently toward three red server blocks in a textured screen print

    AIVAX Labs

    MCP went stateless. Your application did not

    MCP 2026-07-28 removes protocol sessions and transport replay, moving durable state, retries, long-running work, and compatibility into explicit application contracts.

    Read post
  5. Botanical flat lay in cream, pink, and green with pressed leaves, handmade papers, bowls, and a vessel of grains

    AIVAX Labs

    A vector database is not a RAG system

    A vector database stores and searches vectorized records; a managed RAG system coordinates the wider path from source content to maintained, retrievable context.

    Read post
  6. Translucent capsules carried on deep-blue currents pass through gated openings in a porous white boundary into calm terraced channels

    AIVAX Labs

    An MCP server is a trust boundary, not just a tool catalog

    Connecting an MCP server exposes executable capabilities to a model. Discovery policy, call-time authorization, result handling, and audit decide whether the connection is safe — not the tool list.

    Read post
  7. A scaffold bridge carries seed pods, glass vessels and archives from a root-bound grove monolith across a gorge into an open modular garden

    AIVAX Labs

    Migrating from OpenAI Assistants Without Rebuilding the Same Coupling

    The Assistants API shutdown is an architecture migration, not an endpoint rename. Map configuration, state, execution, tools and observability before choosing Responses or an application-owned gateway design.

    Read post
  8. A precision glass-and-metal translator separating layered signals into visible and opaque output channels

    AIVAX Labs

    Reasoning Is a Protocol, Not Just a Model Setting

    Reasoning APIs now carry summaries, signatures, encrypted state and provider-specific stream events. A production gateway must preserve that protocol, not flatten it into text.

    Read post
  9. A monumental stone gateway filtering irregular colored fragments before they enter a calm central chamber

    AIVAX Labs

    Gateway Moderation Is a Product Control, Not Just a Prompt

    AIVAX Gateway Moderation centralizes safety policy, normally evaluating incoming content before model generation while preserving a configured fallback when that separate step is unavailable.

    Read post
  10. A tactile tabletop evaluation with three parallel conversation tracks converging on a final scored outcome

    AIVAX Labs

    Introducing Agentic Tests

    Agentic Tests evaluates complete, goal-oriented conversations through your AI Gateway, with a simulated user and an independent judge tracking the outcome across turns.

    Read post
  11. A broad field of document cards narrowing into a candidate set and then an ordered shortlist

    AIVAX Labs

    Semantic Search vs. Reranking: They Solve Different Problems

    A practical guide to diagnosing retrieval, rank fusion, and reranking—so you improve the stage that is actually failing.

    Read post
  12. Smooth stones arranged in decreasing size on warm sand, representing recurring document retrieval

    AIVAX Labs

    Reflex: retrieval built for recurring documents

    Reflex combines semantic relevance, lexical evidence and account-scoped cache reuse for recurring-document retrieval.

    Read post