AI: uratibu
Uratibu wa AI huunganisha hizo tatu: injini hugundua wakati katika hali ya mtumiaji, huchagua kundi, na huchagua hatua, hivyo kitanzi hufanya kazi bila wewe kuunganisha kila hatua kwa mkono.
At a glance
- GraphQL
aiquery: summarise, explain, suggest- MCP
- Every
prodantix.*tool, callable by an agent - MCP host
https://eu.mcp.prodantix.com- Auth
- Access token for GraphQL; sign in with Bomdisoft for MCP
- Hugundua wakati muhimu katika hali ya papo hapo
- Huchagua kundi sahihi na hatua sahihi
- Hufunga kitanzi: hatua huwa tukio linalofuata ambalo injini hujifunza kutoka kwalo
AI iliyojengwa ndani na nyongeza ya AI
Prodantix ina aina mbili za AI. AI iliyojengwa ndani ni sehemu ya kila mpango na huwa imewashwa kila wakati. Husoma kila ujumbe unapofika na huchagua kati ya majibu yaliyowekwa: kama ni ujumbe taka, kama maarifa yako yanaweza kuujibu, na kama mgeni anataka mtu. Haiandiki kamwe, na haitozwi kamwe kwa kila tokeni. Nyongeza ya AI huandika: Uliza, rasimu na tafsiri za majibu, na majibu ya msaidizi wa messenger. Imezimwa hadi uiwashe, na hutozwa kwa kila tokeni kwa bei ya muundo pamoja na 20%.
Jinsi inavyofanya kazi
Every answer is grounded in rows the caller could already read. Citations are resolved server-side from a built candidate list rather than taken from the model’s reply, so an answer can only point at something that exists and the caller is entitled to see.
Wapi kuifikia
| Surface | Operation |
|---|---|
| GraphQL | ai query: summarise, explain, suggest |
| MCP | every prodantix.* tool, callable by an agent |
Mfano
query Explain($projectId: String!) {
ai {
explainMetric(
projectId: $projectId
metric: "order.completed"
window: "P7D"
) {
summary
citations { kind id }
}
}
}Pointing an agent at prodantix
The MCP surface exposes the same capabilities to an autonomous agent. The agent signs in with Bomdisoft and you choose what it may do; see MCP for connecting one.
{
"mcpServers": {
"prodantix": {
"url": "https://eu.mcp.prodantix.com/mcp"
}
}
}