Roadmap

Welcome to the Kairntech low-code AI platform product roadmap

— last updated April 29, 2026.

If you have a question, a project in mind, or want to learn more about our platform, please contact us !


Caption for the table on the effort required for development
S some days
M some weeks
L some months
XL one semester or more
ID TOPIC SUB-TOPIC EFFORT DELIVERY
1Ingestion pipelineMake content ingestion pipeline more robust: New event-driven architecture (RabbitMQ…), parallel processing, handling errors, progress bar, retry, recovery, failed data management, store original document…XLNew Web Service
2ConnectorsSharepoint connector v2 (call ingest API + ability to configure in the Studio)MConnector & Studio
3Veeva connector?Connector & Studio
4Kairntech Studio Display segments in the document viewMImproved Studio
5Display original documents (PDF viewer, images, video…)SImproved Studio
6New features for creating RAG dataset: Question Generator, Synthetic Answer Verifier, Cross-Chunk Contradiction DetectorLImproved Studio
7New features for creating S2T dataset : audio file playback, text document editing, automatic spell checking, report of the time position in the audio file?Improved Studio
8Improve user onboarding: interactive product tour, use-case based signup, prefilled first project, contextual tooltips, project template library, onboarding assistant, progress checklist, collaborative onboarding, …MImproved Studio
9Improve AI/NLP pipeline configuration: Visual pipeline editor, Real-time validation, Run a pipeline step-by-step, Pre-built pipelines, Fault tolerance, Cost-aware execution, Batch vs. streaming modesLImproved Studio
10Chatbot’s tools configuration: Let the user decide which AI tools (web search, document retrieval, API connectors, etc.) are active for each individual project’s chatbot.MImproved Studio
11Advanced RAGLoop on questions/documents, evaluator LLM (Relevance, Faithfulness, Completeness…), report (per question, per document, global…)MNew Web Service
12Query transformation & normalization (typos correction and spell checking, business vocabulary normalization, cross-lingual normalization, Intent & filter analysis, Query reformulation & expansion, enriched query object)MNew Web Service
13Extensive search (not the top n results of RAG): Query decomposition, Iterative passes over the full knowledge base, Confidence scoring as a stopping condition, Full evidence pool output?New Web Service
14Self-auditing answer engine (trust score): Retrieval confidence, Source grounding, LLM self-assessment, Answer coherence checks, RAG fallback pipeline (Image retrieval, Visual context representation, Vision LLM answer generation)LNew Web Service
15GraphRAG: LazyGraphRAG, KG construction, Hybrid search (fulltext, vector, graph), cross-document entity linking, confidence scoring, explainability, graph optimisation, query routing, cross modal GraphRAG, Agentic GraphRAG, Ontology – OWLXLNew Web Service
16NLP tasksSupport segment classification (categorization project)MNew Web Service & Studio
17Support anaphora resolutionMNew Web Service & Studio
18Support intent & slot filling for event detection (LLM), generate a structured outputSNew Web Service & Studio
19Support relationship extraction (LLM), generate a structured outputSNew Web Service & Studio
20Ability to link entities to any external KGMNew Web Service & Studio
21Provide a normalization framework to populate Knowledge GraphMNew Web Service & Studio
22LLM-assisted active learning (Text Classification, NER)M
23LLM-assisted synthetic data generationS
24Kairntech ChatbotMetadata filtering: Dynamic / User-Declared Filters, LLM tool-calling to convert natural language to structured filtersMImproved Chatbot
25MCP supportSImproved Chatbot
26UI: Chainlit framework replacementMImproved Chatbot
27Multi-agents implementation (LLM)MImproved Chatbot
28Platform MonitoringAccess logS
29User behavior metrics. Automatic weekly reportM
30Deployment & scalabilitySSO-OKTA autentication (Machine-to-Machine)MImproved platform
31LiteLLM product integration & re-engineering (LLM, embeddings)MImproved platform
32Chatbot in K8sSImproved platform
33Elasticsearch scalability (vectorization)MImproved platform
34Incremental processing pipelineLImproved platform
35Sherpa-core in K8s (split Sherpa container: Annotate API vs All-the-rest API, jobs)LImproved platform
36Hot deployment of pymultirole component?Improved platform
37entity-fishing scalabilityMImproved platform
38Technical debtJava upgrade (for k8s)MImproved platform
39Python upgrade 3.12 (only pymultirole components)MImproved platform
40Suggesters components refactoring (python upgrade, updated/clean engines, support of K8s…)LImproved platform
41Suggesters new enginesLImproved platform
42SDK industrialization (documentation, samples, creating & saving new components, deployment…)LSDK
43Quality EvaluationMerge Quality Evaluation Server in Studio (BE & FE) – Support NER & EntityLinkingMImproved Studio
44Support Classification task (confusion matrix…)MImproved Studio
45Support RAG Multimodal (Retriever, Answer generator, with standard metrics and LLM-as-a-Judge)LImproved Studio