#ai#team#data

Conducting an AI-Native Developer Assessment (RS-DEVS)

The AI-native approach helps a PM remove subjectivity, rely on workflow facts, and prepare arguments for growth-focused feedback.

  • Step 1. Collect artifacts (facts base for the PM)
  • Step 2. Initialize the AI and load the context
  • Step 3. Go through the assessment stage by stage (dialog with AI)
  • Step 4. Build the RS-DEVS report and development plan (PDP)

  1. Conducting an AI-Native Developer Assessment (RS-DEVS) 6/4/2025 Author:

  2. The foundational AI-native approach helps a PM remove subjectivity, rely on facts from work processes, and prepare rock-solid arguments for growth-focused feedback.

  3. According to company policy, the engineer's regular review is conducted by

  4. The manager (PM) after the developer completes the self-assessment.

  5. PMs often tend to inflate scores unintentionally because of good relationships within the team or to avoid demotivating an employee. An AI-native approach helps the PM remove subjectivity, rely exclusively on facts from work processes, and prepare rock-solid arguments for developmental feedback before the 1-on-1 meeting.

  6. In this case, AI is not arguing with the manager's "feelings"

  7. , then checks the facts against the strict requirements of the policy.

Step 1. Collect artifacts (facts base for the PM)

  1. The AI does not invent facts; it analyzes the provided data. Before initializing the assessment, the PM must gather raw evidence:

  2. Company policy: Document "101 - IDP and Developer Assessment"

  3. (contains strict criteria for task levels and roles).

  4. What scores the employee gave themselves and how they justify them.

  5. Transcripts of work meetings (key artifact):

  6. Daily meeting recordings (how the developer discusses tasks, whether they understand the business context).

  7. Client meeting recordings (whether the camera is on, whether they speak the language of the business).

  8. Technical sync recordings (whether synchronous code review is used, whether they help colleagues).

  9. Project metrics: Lead Time (time from commit to production), release frequency, usage statistics for automated checks, and the presence or absence of test environments.

Step 2. Initialize the AI and load the context

Use advanced LLMs with a large context window (NotebookLM, Gemini 1.5 Pro, ChatGPT-4o). Upload all collected text artifacts and send the AI the official system prompt approved by the policy: AI prompt: You are the Head of Engineering. You are evaluating a developer using the L10 / L20 / L30 / TECHLEAD / DEVOPS method. Your task is to identify the real level, eliminate self-deception, stop inflation, and define the next development epic. BASIC PRINCIPLES: Round down.

There is no assessment without evidence of independent delivery. There is no L20 without full-stack value delivery. There is no L30 without hypothesis-driven work and a new state. If the client decomposed it, that is L10. If the value was not used in production, it was not delivered. General statements are not accepted - only facts. Proceed step by step, asking me clarifying questions: STAGE

Collecting facts by task. STAGE

Strict check of each task against L10, L20, or L30. STAGE

Assessment of the technical implementation (check for weak coupling). STAGE

TECHLEAD assessment (search for a real strategy to accelerate delivery and influence the team). STAGE

Check for "engineering illusions". STAGE

Comparison with the developer's self-assessment and detection of inflation. STAGE

Create an IDP in coaching mode (next development epic, 3 steps, metric, deadline).

Step 3. Go through the assessment stage by stage (dialog with AI)

Because the prompt includes a step-by-step algorithm, the AI will guide you through the process itself, acting as a strict mentor.

If the AI asks: "Was there direct contact with the user, and did the developer do both front and back independently?", answer honestly based on the transcripts.

Do not try to "push through" an inflated rating:

If you claim the task matches L30, the AI will challenge you with follow-up questions: "How did the project's meta-property change?

Were the hypotheses tested in production?".

If there is no evidence, the rating is automatically adjusted to L20 or L10 according to the rules.

Provide the AI with the scores the developer gave themselves

AI will identify gaps and prepare policy-based arguments for a constructive 1-on-1 dialogue.

Step 4. Build the RS-DEVS report and development plan (PDP)

  1. After successfully completing all 8 stages, ask the AI for the final summary.

  2. You will receive a ready-made report to enter into the system:

  3. Actual task level (L10 / L20 / L30).

  4. Final scores for each RS-DEVS criterion with strict justification.

  5. Feedback block: what exactly is the self-assessment overstatement, if any, and what is the main growth constraint. PDP-TXT (Next step for the development plan):

  6. Define the next development epic, 3 concrete steps for the next 1-3 months, a success metric, and a deadline. With this document, the PM enters the 1-on-1 meeting with the developer, using company standards and indisputable facts, which shifts the conversation from personal preferences to transparent professional growth.

Bottom line: why AI-native assessment outperforms the traditional approach

  1. The main idea of this approach is to separate facts from impressions.

  2. When an algorithm based on policy stands between the manager and the developer, both sides benefit:

  3. The developer gets a transparent, predictable growth system.

  4. It knows exactly which facts are needed to move to the next level and does not depend on the manager's mood.

  5. The manager gets rid of the discomfort of a "subjective verdict".

  6. AI builds the arguments from data - all that remains is to discuss them in a constructive dialogue. The team sees the same rules of the game: the same criteria, the same process, the same bar for everyone. AI does not replace human conversation - it makes it honest. And honest feedback is the only kind of feedback that truly helps people grow.

Discuss the article: Conducting an AI-native developer assessment…

Send via:

By clicking the button, you accept the offer and grant consent to the processing of personal data.

Related Cases

All cases

Related solutions

All solutions
Official PHP SDK for Model Context ProtocolAI business analyst for dataAI assistant for meeting minutes management and analyticsAI meeting notes assistant for sales

Articles on the topic

All articles

Related videos

All videos
34:06 Automation and AI Adoption at PIK Group | Vibe Coding, the Developer Market | Artur Ishmaev Podcast 36:37 Neural Networks Changed IT FOREVER! How to Grow FAST from Junior to Senior with AI? Shorts What “KPI” did Amazon set for developers in the AI era?

News on the topic

All news