A platform for those who provide support on software products. The AI classifies, searches and answers from the manuals. The operator confirms with one click.
The path of every request is explicit and traced: assigned category, confidence reached, sources cited.
A vendor’s knowledge lives in the manuals. The questions do not. Every product carries a corpus of procedures; those who support the customers repeat the same answers, searching by hand. forge_qa puts that corpus to work, whatever the customer base.
Classification with a lightweight model; category correctable by hand.
Knowledge base queried by semantic similarity; sources visible.
Confidence score: above threshold it answers, below it hands off.
One click and the answer becomes official, with audit.
Previously, ratifying an automatic answer cost three steps. Now it is one click: the generated answer becomes the official answer instantly, with operator and closing timestamp recorded for audit.
From automatic answer to resolved, atomic.
The confirmed text is the answer sent to the client.
Who closed it and when, always recorded.
The knowledge base is not programmed, it is fed. From the console you register a product source, upload the documents and re-index: from that moment the product knows how to answer, citing what it has read.
One document container per product: watertight compartments, no cross-contamination between scopes.
Manuals, procedures and notes enter from the console. No code changes required to add knowledge.
Indexing in delta — changed documents only — or full. One click and the corpus is up to date.
A test page shows the health of the base and lets you query it before putting it in front of clients.
The knowledge base does not live on manuals alone: every resolved request generates a candidate “question / answer” entry. Entries become knowledge only after human review.
The entry is born at the moment of resolution, one per request, without ever slowing the operation.
Editable text, inclusion entry by entry. The preview is the document that will be published.
Approved entries enter the product source and it re-indexes. A new draft opens.
Excluded entries stay in the history. The review keeps weak answers out.
Every request is framed into categories with a lightweight model; the category stays correctable.
The document base answers citing sources, with a confidence score on every answer.
Above threshold the answer is automatic; below it passes to human handling.
A good answer closes with a gesture: it becomes the official answer, with audit.
Ownership, resolution, cancellation and reopening: explicit states with history.
Software houses, resellers and clients, with provisioning and per-tenant isolation.
Each product has its corpus. Reseller cap and whitelist decide who sees what.
Tokens and cost tracked per call and per model, with hierarchical spend quotas.
Client master data is never sent to the AI; fonts and resources self-hosted.
Anti-CSRF, TLS, Argon2id hashing, client data never sent to the AI.
forge_qa is multi-tenant by construction. The reseller resells to its clients what the software house grants; each level sees only its own.
Governs the product catalogue, the corpora, the thresholds and sees the entire system. It is the “forge” brand.
Resells to clients within its own product cap; manages and confirms requests.
Submits requests choosing the product; inherits the reseller’s products, unless restricted.
The dashboard reads the real state of requests: how many found an answer on their own, how many required a person, how confidence distributes.
Artificial intelligence is a variable cost. forge_qa makes it visible and governable: measured per call, attributed per model, capped per tenant.
Every call logs the tokens and the estimated cost, with the model that produced it.
Each model is assigned its price per million tokens: the cost of every request becomes a real number.
A monthly spend cap per user or tenant, cascading to descendants.
If the base has no relevant context, the generative model is not called: no expense.
Generation with extended reasoning is the dominant line; classification and indexing weigh a fraction. That is where the optimisation lever applies.
Products are in watertight compartments: every question is routed only to the corpus of the chosen product. The model works for any documented product, in any sector.
Each product has its own document base: no cross-contamination between different scopes.
Defines which products a reseller can offer to its clients.
Further restricts what the individual client sees, within the granted cap.
Every question reaches only the corpus of the chosen product, with its sources.
forge_qa handles client data and their requests. The security posture is not an accessory: it is part of the product definition.
Every reseller and client sees only its own data; the hierarchy is enforced at model level.
Passwords with Argon2id hashing, forced change on first access, signed sessions.
Anti-CSRF middleware on every write, encryption in transit, secure cookies.
The platform restarts on its own after any interruption; the database stays intact.
Only the question text reaches the AI: no client master data.
Fonts and resources self-hosted, in line with a data-conscious posture.
forge_qa is an AYXZA system, in white-label, without giving up client data — whatever customer base you serve.