ACADEMY & TRAINING CATALOGUE

The 3 Official Agentic Engineering Programs.

Certifying engineering modules designed for engineering schools, universities, and business schools seeking to train in autonomous agent architectures, governance, and advanced reasoning.

Official Catalogue

The Qognito.io Training Triad

A "First Principles" approach: API plumbing, strict typing, FinOps governance (Ctask), and reinforcement learning (RLVR).

AVAILABLE 28h (4 Days)

BOOTAG-IA

Building an AI Agent

Autonomous agent architectures from scratch, OOP resilience (R or Python), REST plumbing/JSON Schemas, FinOps telemetry, and EU AI Act compliance auditability (LLM-as-a-Judge).

Consult BOOTAG-IA Sheet ↓
AVAILABLE 14h to 21h

SAGA-IA

AI Agent Architecture & Governance Strategist

Macro-architectural scoping, FinOps governance (Ctask), Spec-Driven Development (SDD), Zero-Trust harnesses, and compliance with EU AI Act requirements (Art. 14).

Consult SAGA-IA Sheet ↓
AVAILABLE 40h (5 Days)

REASON-IA

Reasoning, Emergence & Reinforcement Learning

Deep Tech: Stochastic inference, KV Cache from scratch, RLVR reinforcement learning (GRPO algorithm), Self-Consistency, and distillation towards sober, sovereign models.

Consult REASON-IA Sheet ↓
Partnership & Variations

The Triad for Higher Education & Engineering Schools

Three complementary programs designed to seamlessly integrate into your M1, M2, Engineering, Business School, and PhD curricula:

IMMERSIVE BOOTCAMP (28H)

BOOTAG-IA: Building an AI Agent

For M2 Computer Science, Engineering Students, Data Engineers & Builders. Building autonomous No-Framework agents from scratch.

BOOTAG-IA Partnership Sheet ↓
SCOPING & GOVERNANCE (14H-21H)

SAGA-IA: AI Architecture Strategist

For M1/M2 Management, Executive Ed, Consultants & Junior CIOs. Macro-architectural scoping, Ctask formula, SDD, and EU AI Act.

SAGA-IA Partnership Sheet ↓
DEEP TECH & R&D (40H)

REASON-IA: Reasoning & RLVR

For M2 AI/MLOps, Research Engineers, PhD Students & Data Labs. Autoregressive inference, RLVR (GRPO), and Sober AI distillation.

REASON-IA Partnership Sheet ↓
INSTITUTIONAL PARTNERSHIP SHEET — PROGRAM 1

BOOTAG-IA: Building an AI Agent (28h)

Higher Education & Engineering Schools Partnership (CTI/CGE).

1. Diagnostic & Educational Benefits of BOOTAG-IA

"No-Framework" Engineering:

Building autonomous agents from scratch (OOP in R or Python) interacting directly with REST HTTP APIs.

Encapsulation & Immutable State:

Execution classes (ExecutionContext) and hermetic sub-agents (Agent-as-a-Tool pattern).

Automated Evaluation:

Generating an Evidence Pack certifying deterministic behavior using the LLM-as-a-Judge suite.

2. Tech Stack & R-Native Agentic Architecture (From Scratch)

Unlike overly simplified approaches relying on bloated frameworks, BOOTAG-IA teaches building an agentic harness from scratch in R. This approach guarantees full network control, minimal memory footprint, and industrial isolation without black boxes.

1. REST Plumbing & Black Box Elimination

Leveraging {httr2} to query the official Gemini REST API directly. Full network control: native exponential backoff handling (req_retry), HTTP 429/500/503 error handling, and transparent fallback switching without heavy Python frameworks (LangChain, LlamaIndex).

2. Structured Outputs & Direct JSON Schema

Native JSON Schema specification using nested R named lists passed directly to generationConfig$responseSchema. Guaranteed parsing and type safety without Pydantic via jsonlite::fromJSON.

3. R6 OOP & Strict Encapsulation

The R6 architecture separates truth (immutable R6 ExecutionContext: history, metadata, token budget) from the ephemeral view (LlmRequest). Sub-agents (Agent-as-a-Tool) maintain isolated contexts preventing context poisoning.

4. Data Sobriety & Native Tidyverse

RAG and memory implemented via the tidyverse (dplyr, purrr): chunking, embeddings via embedContent, and manual cosine similarity computed from scratch without heavy vector DBs like ChromaDB.

5. Agnostic Lightweight Client via MCP

The R agent acts as a universal lightweight client via the Model Context Protocol (MCP), dynamically orchestrating remote tool servers written in Node.js, Python, or Go.

6. Hermetic Software Factory ({renv})

Industrial isolation guaranteed by {renv} and its renv.lock lockfile, eliminating dependency conflicts frequently encountered in Python environments (Conda, Poetry, Pyenv).

3. Curriculum Outline & Detailed Syllabus (16 Modules / 28h)

Structured progression in 4 progressive engineering sections. Each module delivers a new tool or R/Python class in the learner's toolbox:

Section 1: LLM Foundations & Structuring
  • Mod. 1.1: Modeling, REST & Network Resilience
  • Mod. 1.2: Authority System Prompt & SessionManager
  • Mod. 1.3: Structured Outputs (JSON Schema)
  • Mod. 1.4: Sequentiality & GAIA Benchmark
Section 2: MCP Protocols & ReAct Loop
  • Mod. 2.1: Tool Discovery & REST Protocols
  • Mod. 2.2: OOP Tools Standard & MCP Protocol
  • Mod. 2.3: Centralized ExecutionContext & Interfaces
  • Mod. 2.4: Autonomous ReAct Engine (Think-Act-Observe)
Section 3: RAG, Exploration & Memory
  • Mod. 3.1: RAG & In-Memory VectorStore (768d)
  • Mod. 3.2: Autonomous Structure Exploration
  • Mod. 3.3: Long-Term Memory & Multi-Run Compaction
  • Mod. 3.4: Discovery & Agent Skills (YAML/SKILL.md)
Section 4: Multi-Agents, Telemetry & CI/CD
  • Mod. 4.1: Metacognition, Planning & Reflection
  • Mod. 4.2: Multi-Agent Orchestration (Agent-as-a-Tool)
  • Mod. 4.3: Telemetry & Observability (Trace ID)
  • Mod. 4.4: Quality Flywheel (LLM-as-a-Judge) & CI/CD

Integrate the BOOTAG-IA Bootcamp (28h) into your Curriculum

Discuss with Boris Guarisma →
INSTITUTIONAL PARTNERSHIP SHEET — PROGRAM 2

SAGA-IA: AI Agent Architecture & Governance Strategist (14h to 21h)

Modular Course for Business Schools, Executive Education, Management Masters & CIO Tracks.

1. Diagnostic & Educational Benefits of SAGA-IA

FinOps Governance & Ctask:

Real-time token monitoring probes and financial circuit breakers.

Spec-Driven Development (SDD):

Drafting structured workflow contracts to eliminate Context Rot.

Zero-Trust & EU AI Act (Art. 14):

Anti-injection harnesses, Human-In-The-Loop (HITL) protocols, and emergency stop switches.

2. Format, Duration & Target Audience

Flexible Modular Format (7h to 21h):

Tailored per audience: 7h (Decision makers & CIOs), 14h (Delivery & Project Managers), 21h (Tech Consultants & Executive Ed).

Stack & Standards:

Leverages Google Gemini hierarchy (3.5-flash-lite for evals, 3.5-flash for execution, 3.5-pro for reasoning), Spec-Driven Development (SDD) and XML/Markdown contracts.

3. Curriculum Outline & Detailed Syllabus (5 Sections / 10 Modules)

Macro-architectural structure across 5 pillars of scoping, wiring, and industrial governance:

Section 1: FDE Transition & Arbitrage
  • Mod. 1.1: Accounting arbitrage (Full Ctask cost)
  • Mod. 1.2: Last mile of physical system wiring
Section 2: Harness Anatomy & Governance
  • Mod. 2.1: 5 Agentic bricks & GAIA Benchmark
  • Mod. 2.2: Private Harness vs EU AI Act (Art. 14)
Section 3: Spec-Driven & Context Eng.
  • Mod. 3.1: Infinite window & Multi-model compaction
  • Mod. 3.2: Spec-Driven Development (SDD contracts)
Section 4: IT Security & Zero-Trust
  • Mod. 4.1: PocketOS Post-mortem & Attention Asymmetry
  • Mod. 4.2: Fatal Triad (Simon Willison) & Sandboxing
Section 5: Industrialization, Evals & Judge Pattern
  • Mod. 5.1: Generator-Judge Pattern & Quality Flywheel
  • Mod. 5.2: Reversibility Grid, Session Freezing & Human-in-the-Loop (HITL)

Integrate the SAGA-IA Module (14h to 21h) into your Curriculum

Discuss with Boris Guarisma →
INSTITUTIONAL PARTNERSHIP SHEET — PROGRAM 3

REASON-IA: Reasoning, Emergence & RLVR (40h)

Deep Tech Track for M2 AI/MLOps, Research Engineers & PhD Candidates.

1. Diagnostic & Educational Benefits of REASON-IA

KV Cache & Autoregressive Inference:

Low-level PyTorch/R tensor memory writing and stochastic decoding (Top-p, Temperature, Self-Consistency).

RLVR & GRPO Algorithm:

Reinforcement learning with verifiable rewards: relative advantage normalization and KL penalty.

Distillation & Sober AI:

Chain-of-thought capture (Thought) and Masked Cross-Entropy distillation towards compact embedded models.

2. Tech Stack & Hybrid Sobriety (R & PyTorch via reticulate)

Hybrid Sobriety: Leveraging reticulate allows leveraging heavy PyTorch tensors while preserving a lightweight, fluid, and testable R-native orchestration.

Why the Alliance of R & {reticulate} is Best Practice?

  • The "Python-Only Overkill" Syndrome: Wanting to write everything in Python (statistical analysis, budget modeling, unit testing, data visualization) leads to unnecessary over-complexity compared to R's native power.
  • The Optimized Hybrid Approach:
    • Leave heavy compute to the heavy lifters (Python/CUDA): PyTorch tensors and neural network computations run in C++/GPU on the Python side.
    • Leave control to the rigorous engine (R/Tidyverse): I/O (downloads), logit analysis, latency visualizations ({ggplot2}), compliance tests ({testthat}), and orchestration are written in R.
  • Takeaway: Ultra-smooth IPC (Inter-Process Communication) with negligible overhead compared to LLM inference time.

3. Curriculum Outline & Detailed Syllabus (8 Sections / 32 Modules / 40h)

Intensive 5-day Deep Tech program covering the complete chain from reasoning to RLVR:

Section 1: Reasoning Foundations
  • System tokens & Raw logits
  • Greedy vs Multinomial sampling
Section 2: Autoregressive & KV Cache
  • Rollout loops & Inference
  • KV Cache from scratch in PyTorch/R
Section 3: Symbolic Evaluation
  • Brace parser & SymPy
  • Parallel MATH-500 benchmark
Section 4: Inference-Time Compute
  • Top-p Filtering & Temperature
  • Self-Consistency & Majority voting
Section 5: Self-Refinement
  • Logprobs & Semantic uncertainty
  • Feedback & Iterative correction
Section 6: Reinforcement (GRPO)
  • RLHF vs RLVR (verifiable rewards)
  • GRPO Normalization & Policy Gradient
Section 7: GRPO Stabilization
  • Entropy, Clipped Ratios & KL Divergence
  • Format Rewards & Anti-reward hacking
Section 8: Distillation & Sober AI
  • Teacher Curation & Answer-Only SFT
  • Masked Cross-Entropy & Sober models

Integrate the REASON-IA Bootcamp (40h) into your Curriculum

Discuss with Boris Guarisma →

Integrate the REASON-IA Bootcamp (40h) into your Curriculum

Discuss with Boris Guarisma →