Codvo InternalInternal certificationby Codvo AI Engineering & Architecture Lead Team

Codvo Internal L2 — Agent Systems Builder

Working controlled agent prototype with tools, data, approvals, observability.

Cost

Free

Duration

Unset

Levels

1

Materials

Ready

Before you start

Prerequisites

codvo-l1-practitioner

Recommended for

Open to all employees

Decision brief

Codvo trial, not a course link.

Use this catalog item when the employee needs a governed internal certification attempt with evidence and board review.

Where work happens

Inside CertOps

The governed trial, clock, evidence package, AI handoff, and board review stay in this app.

Before start

Prepare untimed

Learners can read, plan, and inspect the rubric before starting the official attempt.

Attempt structure

1 level

Employees choose a level, apply, then start the timed certification trial when approved.

What proves it

Capstone decision

A durable submission plus human review decides pass, refer, or fail. AI review is advisory.

Internal attempt model

This runs inside the CertOps attempt workflow.

Codvo internal certifications are not provider courses. CertOps manages approval, timing, capstone evidence, AI review, board review, and badge issuance.

proof-led completion

Prepare

Untimed

Read the material and rubric before starting. Planning time is not counted against the attempt window.

Attempt

Timed

Start only when ready. CertOps records elapsed time, pauses, deadline, and submitted evidence.

Decision

Board

Claude review is advisory. Human reviewers make the pass, refer, or fail decision.

Native CertOps control

Hosted and verified inside CertOps

Codvo internal certifications run as controlled attempts: approval, timing, capstone evidence, AI handoff, board review, and badge issuance all stay inside CertOps.

high trust

Hosting

CertOps

Materials, attempt clock, evidence, and review decisions stay in the app.

Iframe

Not needed

There is no external provider page to embed for internal certification attempts.

Verification

Board

Human reviewers make the credential decision; AI review is advisory.

Control signals

  • Timed attemptCertOps records start, pause, elapsed time, deadline, and submission timing.
  • Capstone evidenceEmployees submit the PR, artifact, or delivery evidence requested by the rubric.
  • Provider importNot applicable for native Codvo internal certifications.

Attempt structure

Levels and scoring

1 level

L2 Builder

Target 4wPass ≥ 80%

Rubric (v1)

  • End-to-end functionality

    20% weightScored
  • Architecture and runtime design

    15% weightScored
  • Tool and data controls

    20% weightMust pass
  • Observability and evaluation

    20% weightMust pass
  • Security and failure handling

    15% weightMust pass
  • Technical documentation

    10% weightScored

Learning plan

Course material

Full curriculum, deliverables, capstone, and pass criteria.

Duration

4 to 6 weeks, with weekly labs and a final prototype review

Audience

AI engineers, backend engineers, data engineers, QA automation engineers, DevOps engineers, hands-on technical leads.

Prerequisite

Level 1 certification (or equivalent internal waiver from the review board)

Purpose

Certifies that a practitioner can build a working controlled agent prototype and demonstrate practical engineering discipline around tools, data, approvals, evaluation, and observability.

Competencies — practitioners must be able to

  • Design agent runtime patterns: stateless, workflow-based, or durable
  • Implement tool calling with constrained permissions
  • Integrate at least one governed data source or curated knowledge base
  • Apply basic retrieval quality checks
  • Add human approval before sensitive actions
  • Capture traces for model calls, retrieval, tool calls, and decisions
  • Create a practical evaluation set
  • Test for prompt injection, wrong tool use, and unsafe outputs
  • Implement a cancellation, rollback, or kill-switch mechanism
  • Document production gaps and hardening requirements

Learning modules

  1. 1Agent runtime and workflow orchestration
  2. 2Tool integration and MCP-style patterns
  3. 3Governed retrieval and semantic data access
  4. 4Identity and delegated authorization basics
  5. 5Human-in-the-loop workflow design
  6. 6Observability, traces, and cost monitoring
  7. 7Agent testing and evaluation
  8. 8Failure handling and rollback

Required deliverables

  • Working prototype
  • Technical Architecture Document
  • Agent Flow Diagram
  • Tool and Data Access Matrix
  • Evaluation Plan
  • Test Evidence
  • Observability Trace Sample
  • Risk and Control Register
  • Production Readiness Gap List

Practical capstone

Customer Support Resolution Agent — workflow: read ticket → retrieve KB content → review customer history/policy data → draft response → human approval → log all calls/retrievals → capture feedback (accepted/edited/rejected).

Assessment method

Demo, artifact review, technical Q&A. Weighted: functionality (20%), architecture (15%), tool/data controls (20%), observability (20%), security/failure handling (15%), documentation (10%).

Pass criteria

Score ≥80% overall. MUST demonstrate working observability, constrained tool access, and one approval/interrupt pattern. A prototype that works but cannot be inspected or controlled does NOT pass.

Certification attempt

How this internal attempt works

Start the trial when you are ready to be timed. Submit the capstone PR and evidence before the deadline.

  1. 1

    Apply first

    Your request goes to the right manager, L&D owner, or review board before the timed attempt opens.

  2. 2

    Start trial

    The clock starts only when the attempt is approved and you choose to begin. CertOps records that timed certification trial from start to submission.

  3. 3

    Submit evidence

    Attach the capstone PR or artifact link before the deadline so CertOps can queue AI and board review.

  4. 4

    Get a decision

    Reviewers score the rubric, request rework when needed, or pass the attempt and issue the credential.

Sign in to enrol