Voice agent · Custom HTTP guide · Pathway webhook + post-call webhook

Northsun + Bland AI

This guide maps Mnemix's frozen caller-memory API to Bland's documented Pathway webhook and post-call webhook capabilities. It is a custom HTTP guide, not a native or certified adapter.

What

Mnemix is the memory and enrichment layer for AI agents. Governed context intelligence is the differentiator.

Who

For teams building voice, chat, coding, and workflow agents that need persistent, inspectable context.

Price

Hobby is $0. Paid access is Contact sales.

How

Use the frozen caller REST contract for recall, durable call write-back, and read-only caller lookup. Use authenticated MCP only for the broader beta context tools enabled and proven for your tenant.

For agents

On an inbound call your voice agent receives the caller profile, this tenant's prior-call memory, and available Trestle and Twilio Lookup enrichment as contextual evidence before its first sentence; after hangup the call is submitted and committed durably before the response returns, visible on the very next read.

What Northsun adds to Bland AI

• A caller-memory lookup you control. Your server decides where Bland's documented webhook or outbound orchestration calls Mnemix.
• Explicit normalization. Map Bland's current payload into the frozen Mnemix request shape and test that mapping with controlled calls.
• A proofable boundary. A successful recording proves the exact Pathway or post-call configuration shown; it does not establish a native adapter.

How to connect Bland AI to Northsun

1. 1

   Choose the Bland event

   Use Bland's current official documentation to select a Pathway webhook, outbound pre-call step, or post-call webhook for the lifecycle moment you need.

2. 2

   Recall before context is needed

   Call POST /v1/recall_and_enrich from your server and inject only the fields your Pathway uses.

3. 3

   Normalize the completed call

   Verify the Bland webhook signature and map its call identifier, caller number, transcript, duration, and outcome into POST /v1/calls/end.

4. 4

   Prove the write-back

   The interaction is committed durably before calls/end responds; retain the Mnemix trace ID and confirm it with a later recall.

Custom HTTP pattern

Adapt this boundary to the current vendor payload and verify it with controlled events before production.

async function callMnemix(path: string, body: unknown) {
  const response = await fetch(`https://mcp.mnemix.ai${path}`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.MNEMIX_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify(body),
  });

  if (!response.ok) {
    throw new Error(`Mnemix request failed: ${response.status}`);
  }

  return response.status === 204 ? undefined : response.json();
}

// Before an outbound call, or from an appropriate Pathway webhook node:
const packet = await callMnemix("/v1/recall_and_enrich", {
  phone_number: callerNumber,
  trigger: "ringing",
  session_id: blandCallId,
});

// In your verified post-call webhook handler:
await callMnemix("/v1/calls/end", {
  phone_number: callerNumber,
  session_id: blandCallId,
  transcript: normalizedTranscript,
  duration_s: durationSeconds,
  outcome: mappedOutcome,
});

FAQ

Is this a native Bland integration?

No. It is a custom HTTP mapping between documented Bland webhook capabilities and Mnemix's frozen REST endpoints.

Which enrichment vendors may appear?

Mnemix's public enrichment providers are Trestle and Twilio Lookup. Individual blocks may be null.

Where should recall run?

Use an outbound orchestration step or a Bland Pathway webhook position that your own end-to-end test proves meets the conversation deadline.

Last updated: 2026-08-18.