Skip to content
DAQ Consulting, home
Service 02 / 05

AIEngineering.

AI engineering consulting for systems your team can operate. We build retrieval-augmented generation and agent workflows with permission-aware access, evaluation, controlled tool use and production observability.

01 / Paradigm Shift

Evolution of AI

Current

Isolated Prototypes

A promising model demo still needs reliable retrieval, access controls, evaluation and a deployment path before people can depend on it in their work.

Target

Governed AI Systems

Connect approved knowledge and scoped tools to the workflow. Evaluate releases against representative tasks, trace failures and require approval before consequential actions.

02 / Methodology

Neural Foundry

01 / Reasoning01 / 03

Cognitive Architecture

Select and adapt models for the task, retrieve permitted evidence, and compose context that lets an answer point back to its sources.

  • Foundation models
  • Fine-tuning
  • Evidence retrieval
Selected evidence composes contextSelected source passages keep their distinct signatures as they join an assembled context. Other passages remain outside it. Selection is illustrative and does not establish that an answer is correct. Conceptual marks, not measured quantities or production records.

Make the answer inspectable.

Retrieve
Select relevant source material within the caller’s access permissions.
Compose
Build context from the question, permitted evidence and task instructions.
Answer
Cite supporting passages and check important claims. Citations alone do not prove correctness.
02 / Execution02 / 03

Tool Integration

Expose internal APIs and SQL tools through MCP, then enforce identity, scope and action policy at the application boundary.

  • MCP servers
  • Internal APIs
  • Scoped access
Application policy before tool dispatchRequests meet the host application's policy boundary before permitted calls reach tool interfaces. Held requests stay on the caller side, and separate result paths return from the tools. MCP itself does not grant permission. Conceptual marks, not measured quantities or production records.

Authorize every tool call.

Protocol
MCP describes and invokes tools. It does not grant business permissions.
Policy
Enforce identity, scopes and action rules in the application and downstream API.
Approval
Hold consequential writes for human approval when the action policy requires it.
03 / Oversight03 / 03

Governance Protocol

Test agent behavior before selecting a release, and route consequential actions to human review when their policy requires it.

  • Evaluation cases
  • Release gates
  • Human review
Evaluation evidence before an agent releaseA candidate fans out into representative evaluation evidence. The evidence reaches a release gate before an approved version continues. This pre-deployment decision is separate from authorization of actions at runtime. Conceptual marks, not measured quantities or production records.

Release against clear criteria.

Evaluate
Test source attribution, access refusal and action routing with representative cases.
Release
Review the candidate’s evaluation evidence against agreed acceptance criteria.
Runtime
Apply action policy on each run and retain decisions for oversight and review.
03 / Trust & Safety

Secure By Design

Representative traceFive requests. Three controls.
Inspect a request
Blocked01 / 05

Deterministic guardrails

The rule is evaluated before execution rather than inferred from a prompt. The agent never reached the table, so nothing sensitive could enter its reasoning in the first place.

Request
agent.query
Target
customer_pii
Recorded
  1. 01Deterministic guardrails
  2. 02Audit trails
  3. 03Human oversight
04 / Core Architecture

Agentic Stack

  1. Reason

    The model proposes an answer or a tool call.

  2. Authorize

    Host policy checks scope and required approvals.

  3. Execute

    Permitted calls reach enterprise tools through MCP.

  4. Observe

    Tool results return as context for the next step.

Agentic System

Inference
Execution
Inference & reviewAI hostSupplies the objective and receives the final response. Input content does not grant additional permissions.User Intent REQUEST / RESPONSEBuilds model context and feeds tool results into the next turn. Completion, cancellation and configured limits stop the run.Agent Runtime AGENT LOOPHost policy checks arguments, scope and required approvals before its MCP client dispatches calls. Held or denied actions are not sent.Tool Gateway MCP CLIENTValidates and authorizes MCP tool calls, invokes system adapters and returns results to the host client.MCP Server TOOLS / ACCESSExisting APIs, data platforms and jobs execute scoped requests. Their own permissions still apply.Enterprise Systems APIS / DATA / JOBSReturns an answer or proposed tool call from selected context. The application controls execution.Model API CONTEXT / OUTPUTApproves or rejects an action when host policy requires review. Held or rejected calls are not dispatched.Human Review WHEN REQUIRED
Technical notes & sources

Reference architecture reviewed 7 September 2026.

MCP boundaries. One client communicates with one server; the host can manage several clients. Servers advertise supported tools, resources and prompts. This drawing follows an MCP tool call; native API adapters are another integration choice. Standard transports are stdio and Streamable HTTP. The HTTP authorization specification applies to protected HTTP servers; local stdio credentials are managed separately. MCP architecture, transports and authorization.

Runtime and context. Model inference, tool execution and stored run history are separate concerns. Checkpoints support recovery; selected context controls what enters each model call. Completion, cancellation and step or time limits bound the run. Retrieval and long-term memory are optional and do not require a vector database. Sandboxes and specialist agents depend on the task. Runtime separation, context engineering and persistence.

Action controls. Tool results do not confer authority. Input validation, least-privilege access and policy-based approval govern execution. Generated code needs a constrained execution environment. Record redacted events and evaluate model, prompt and tool changes before release. Bound retries and use idempotency or deduplication so resuming work does not duplicate a business action. Tool security, approval and resumable execution, and agent evaluations.

Optional delegation. A2A can connect independently deployed agents. It is a separate interoperability choice, not a required hop in every tool call. A2A overview.

05 / The Interface

Agent Chat

06 / Delivery & platforms

From design to delivery.

Your team receives the application and configuration, an evaluation set, release checks and operating instructions. Model and platform selection follows the task, data boundaries, latency and cost requirements.

Case study · Databricks

A governed knowledge agent.

Permission-aware retrieval, answers with sources and evaluation before release. Follow the engineering decisions from document ingestion to the application.

  1. 01Data Engineering
  2. 02AI Engineering
  3. 03Analytics
  4. 04Migration
  5. 05Managed Services
Next serviceAnalytics