Intelligence as a platform

One foundation.
Every AI capability.

Connect models, knowledge, memory and agents through one governed platform. Give every application intelligence that understands its context.

01Stable contracts
02Connected intelligence
03Governed execution

The SoftKit AI ecosystem

A shared intelligence layer.
Across every product.

Applications own business workflows. AI Foundation connects context, reasoning and execution. Infrastructure runs inference; Admin Console administers the platform.

05Products & applicationsConsume capabilities
04Admin ConsoleAdministers and observes
03Software Factory ↗Builds verified software
02AI FoundationRoutes, plans and reasons
01AI InfrastructureExecutes inference
01 — 04

Why AF

Build intelligence once.
Use it everywhere.

Unify model access, organizational knowledge, agent execution and policy. Reuse the same foundation across assistants, document workflows and software development.

Fragmented context
Duplicated integrations
Opaque consumption
Provider lock-in

Intelligence as a platform

Everything your applications
need to work intelligently.

01

Capabilities, not model dependencies

Chat, generation, summarization, extraction and classification behind versioned APIs and SDKs.

02

Agents with a clear purpose

Plan, act and observe with tools, step budgets, approval checkpoints and controlled autonomy.

03

Knowledge with continuity

Connect organizational sources, semantic retrieval and persistent memory to every conversation.

04

Context and prompts under control

Assemble relevant context within token budgets. Version, render and evaluate reusable instructions.

05

Security throughout execution

Identity, tenant isolation, policies, protected secrets and input/output controls accompany every action.

06

Visibility, capacity and accountable cost

Trace execution, attribute consumption, apply budgets and coordinate capacity across applications and replicas.

Portfolio

Explore the whole platform.

Twelve connected capability families. Open any family to see what it brings to your applications.

01

AI services and structured results

Chat, streaming, completion, summaries, extraction and classification; JSON Schema validation and bounded repair; native structured output, partial-result streaming and schema inference from Go types.

02

Knowledge and retrieval

Source connectors, ingestion, chunking, embeddings, vector search, reranking, reindexing and retention. Hybrid ranking, semantic chunking, multimodal ingestion, provenance, ontology traversal and governed federated knowledge.

03

Memory and context

Session, agent, user and organization memory; write, search, compact, forget and export. Token budgeting, deterministic assembly, adaptive ranking, shared sessions, multimodal context and context caching. Federated memory, custom scopes and replay. Versioned prompt templates, variables and conditions, test-gated publication, no-code multilingual authoring, LLM-as-judge evaluation, feedback optimization and shared template marketplaces.

04

Agents and tools

Plan–act–observe, permissions, approvals, cancellation and resumability. Multi-agent coordination, replanning, parallel tools, dynamic definitions, declarative pipelines, sandboxed code execution and agent/tool marketplaces.

05

Models and providers

Capability-based routing, stable aliases, retry, fallback and real-time streams. Self-hosted endpoints, model discovery, custom aliases, A/B and canary splits, adaptive selection, speculative execution and fine-tuning pipelines.

06

Security and data location

Verified identity, exact administrative scope, tenant isolation, PII redaction and output filters. Injection detection, quarantine, secret rotation, regional residency, DLP, customer-managed keys, moderation and behavioral anomaly detection.

07

Governance and administration

Versioned policies, approvals, publication and activation. Policy simulation, decision history, configuration validation and rollback; integrity-verifiable audit export and federated security policies.

08

Cost and distributed capacity

Source-recorded usage, workspace/application showback, CSV/JSON export and budget alerts. Cost-aware alias substitution, response caching, distributed quotas, leased reservations and FIFO provider admission.

09

Batch processing

Durable jobs and item results, concurrency limits, cancellation and recovery. Provider batch or Router dispatch, summarize/extract pipelines, cross-tenant packing, priorities, webhooks and submission reconciliation.

10

Observability and feedback

Traces, structured logs, metrics and health. Ratings, corrections and flags; opt-in content inspection, quality scoring, regression analysis, aggregate benchmarks, cost/latency anomalies and long-term telemetry retention.

11

Multimodal intelligence

General chat, software development, embeddings, retrieval and reranking; document analysis, OCR, image understanding, speech recognition and synthesis, image generation, video understanding, reasoning, planning and simulation.

12

Runtime, SDKs and deployment

Typed services, module lifecycle, health and controlled shutdown. Dynamic/remote modules, hot reload, marketplaces, SDKs, external APIs, self-service catalogs, multi-region and dedicated deployments, online migrations and adaptive scaling.

Stable contracts

From a request to a contextual result.

  1. 01AuthenticateIdentity and tenant
  2. 02AssembleKnowledge, memory, prompts
  3. 03RouteCapability and eligible model
  4. 04ExecuteInference and tools
  5. 05ProtectFilter and retain
  6. 06ObserveResult, usage and trace

Architecture

Clear responsibilities.
Composable intelligence.

AI Services is the application boundary. Context, agents, memory and knowledge cooperate through explicit contracts. AI Router selects execution; connectors isolate providers. Kernel owns composition and lifecycle.

  • Kubernetes-native and infrastructure-independent
  • Replaceable providers, models and runtimes
  • Structured events, logs, metrics and provenance
  • Fail-closed boundaries and least privilege

Governed execution

Policy, enforcement and evidence.
Each with its own owner.

01 / GOVERNANCE

Define

Governance versions, reviews and publishes policy, with explicit approvals and activation.

02 / SECURITY

Enforce

Security evaluates authorization and protects data at the execution boundary.

03 / OBSERVABILITY

Observe

Observability records execution, consumption and health. Administration exposes controlled operational access.

The outcome

“Connect your applications to shared intelligence, organizational knowledge and governed action.”
Reusable capabilitiesFull traceabilityPersistent knowledgeCost accountability

SOFTKIT AI FOUNDATION

Give every product
the same intelligence foundation.

Build assistants, document workflows and software automation on shared AI capabilities.

Back to the beginning