Slide contents

1. 1. AI in SDLC: from assistants to agents

   Copilots, MCP/A2A, AlphaEvolve, SE 3.0 and large fintech cases

2. 2. Alexander Polomodov

   Technical Director & Fellow, large fintech

   Architecture and engineering practices in fintech

   AI in SDLC across thousands of engineers

   Podcast «Code of Leadership», @book_cube

3. 3. From tools to measurable outcomes

   Why agents emerged, how to build them, and how to measure their effect

   Why agents became possible

   How engineering work changes

   How agents enter the SDLC

   How impact differs from usage

4. 4. 01. Previously on this show

   How we integrate AI into SDLC — big tech cases

5. 5. Agents continue the tooling evolution

   The previous talk covered AI integration; this one follows the autonomous loop

   Assistants already live in tools

   Autonomy is the next step

   Agents need a shared platform

   Outcomes still need proof

6. 6. 02. Assistants → agents

   From autocomplete to autonomous task execution

7. 7. Assistants became everyday tooling

   Copilot and Cursor opened the path; Claude Code and Codex pushed agent mode

   Copilot: agent mode

   Cursor: AI-centered IDE

   Claude Code: terminal agent

   Codex: long-running tasks

8. 8. An agent owns the task loop

   The human states the outcome and decides how deeply to inspect the result

   Plans its own steps

   Calls external tools

   Acts without step-by-step commands

   Returns a result to the human

9. 9. 03. Protocols: MCP and A2A

   Standards for agents and integrations

10. 10. MCP connects tools; A2A connects agents

    The protocols solve adjacent problems and can work together

11. 11. 04. Research and economics

    Why agents are real and here to stay

12. 12. Three forces push the industry toward agents

    Investment demands returns, business demands efficiency, and the market expects promised outcomes

    Billions invested since 2023

    Pressure on company efficiency

    Promises from AI providers

13. 13. AlphaEvolve improves programs through an evaluator

    An LLM proposes a change, a metric tests it, and the database retains better versions

14. 14. A measurable evaluator turns search into impact

    Google applied one loop to infrastructure, hardware, and model training

    Borg scheduling: +0.7%

    TPU circuit optimization

    Faster matrix computation

    Gemini training: +1%

15. 15. People do not want every feasible automation

    Compare worker desire with the actual capability of current agents

    Green light — Wanted by workers, feasible today

    R&D — Wanted by workers, not feasible yet

    Red light — Feasible today, unwanted by workers

16. 16. Agent economies need deliberate rules

    The authors prefer designed sandboxes over an emergent, permeable market

    Low risk

    Permeable sandbox

    Rules designed up front

    High risk

    Bounded sandbox

    Rules designed up front

17. 17. 05. SE 3.0 — AI-Native Engineering

    A new paradigm of software development

18. 18. SE 3.0 moves the interface from code to intent

    An AI-native process connects human requirements with machine implementation

    SE 1.0: code-first + tools

    SE 2.0: code-first + AI

    SE 3.0: intent-first + dialogue

    Humans define requirements

19. 19. Start with the developer goal, then choose tools

    The developer journey links SDLC stages, durable goals, and platform teams

    Gather information

    Plan and gain approvals

    Develop, test, and commit

    Release and operate

20. 20. 06. Large fintech case

    Spirit and agent mode in production

21. 21. Agent-first starts with the whole platform

    Spirit spans work intake and knowledge through infrastructure and production readiness

    Process, search, and documentation

    VCS, IDE, CI, and builds

    Delivery, cloud, and components

    Observability and incident management

22. 22. Agents must cover the whole SDLC

    The engineer sets direction, designs the system, and reviews the output

23. 23. 60% of time is not code writing

    Web and mobile team analysis: an AI program cannot stop at autocomplete

    Creation

    Code — ~40%

    Tests — ~15%

    Coordination

    MR / code review — ~15%

    Jira — ~12%

    Wiki — ~12%

24. 24. Agents move beyond the IDE

    Teams choose painful jobs across the lifecycle

    Code: complete a task end to end

    Data: request → code → chart

    QA: description → test case

    Each profession chooses its jobs

25. 25. 07. Agents in production

    T-Cover Agent, AI code review, security

26. 26. T-Cover proposes only validated tests

    Change → coverage need → candidates → validation → MR for a developer decision

27. 27. Lower baseline coverage yields larger gains

    Added coverage declines as the existing test base grows

    Up to 66%

    0–20% → +40 pp

    21–47% → +33 pp

    47–66% → +27 pp

    Above 66%

    66–73% → +23 pp

    73–89% → +12 pp

28. 28. AI review starts with context

    GitLab, docs, Jira, and instructions feed classification and comment ranking

29. 29. A security agent sees code, not every control

    SafeLiner finds a vulnerability and proposes a fix, but may miss infrastructure mitigations

    Scans the repository

    Explains the finding

    Offers a one-click patch

    May miss infrastructure protection

30. 30. 08. Measuring impact

    Usage is only the first level of evidence

31. 31. Utilization starts; impact still needs proof

    Measure usage first, then impact, then cost and return

32. 32. Usage grew; impact still needs proof

    Internal data clearly establishes adoption and retention

    Created artifacts

    IDE H1: 10%

    IDE H2: 25%

    Heli: 5% → 10%

    Retention · 4 weeks

    IDE: suggest 79%, chat 55%

    Heli: suggest 70%, chat 46%

33. 33. The Russian market needs a comparable baseline

    The study connects practices, engineer perception, and measurable outcomes

    Practices across Russian companies

    Quality and efficiency

    How engineers perceive AI

    Comparison with global trends

    ai4sdlc.tbank.ru

34. 34. Agentic development is a system

    Five conclusions from research and production cases

    Protocols connect the ecosystem

    Evaluators turn search into outcomes

    Platforms span the entire SDLC

    Engineers state intent and review

    Utilization is not impact

35. 35. Sources behind the argument

    Research on discovery, work, agent economies, SE 3.0, and measurement

    AlphaEvolve · Google DeepMind

    Future of Work · Stanford

    Virtual Agent Economies · Google

    SE 3.0 · Measuring AI · DX

36. 36. Thank you!

    polomodov.tech

    All slides and links are in the Telegram channel

    Alexander Polomodov, Technical Director & Fellow, large fintech

    @book_cube