Which SDK do you default to?

None. Multi-turn tool use with reflection before writes tends to be Claude. Structured routing tends to be OpenAI. Long cyclic work with approval gates tends to be LangGraph. The step decides.

Can Agentforce call our Python agent?

Yes, as a peer over A2A through the gateway, with the user’s identity carried across. Not as a shared key pointed at an internal URL.

Do you replace existing automation?

Not on day one. Deterministic automation that works stays. We move the steps that need judgement, and say which ones do not.

Runtime plane

Not every step deserves a model.

Cut the process into steps, mark each one deterministic or adaptive, then choose the runtime. Agentforce where the permissions already live, a code agent where the exception lives, and a plain function where nothing needs judgement.

Get the written assessment Runtime questions

Founded 2022 · Founder in the Salesforce MVP Hall of Fame · Dubai HQ · Kochi studio

What it is

Four runtimes, one classification.

The runtime plane is where a step actually executes. Choosing it is a two-question test: is the step deterministic, and is a human waiting on it?

Classify first

One process, step by step.

Step 1
Cut the process into steps
From the trigger to the last write.
Step 2
Mark each step
Rule or judgement. A person watching, or nobody.
Step 3
Rules stay rules
Flow or a workflow. No model where a rule will do.
Step 4
Judgement gets a runtime
Agentforce in the org, a code agent outside it.

Runtime selection follows the step, not the licence.

Why it matters

One runtime for everything is how programmes stall.

If you have only one seat to put work in, you will put the wrong work in it. These are the four we find.

Peers

Agentforce is a peer, not the ceiling.

Agent-to-agent delegation with the user’s identity carried across the wire. The gateway still sees every hop.

01
Declared skills
Each agent publishes what it can do and what scopes it needs. A registry, not a prompt that lists its friends.
02
A2A delegation
One agent asks another as a peer over a standard envelope, instead of a private wrapper per pair.
03
Identity travels
The user’s authority carries forward, so delegation cannot become privilege escalation.
04
Hop budgets
Traces, max hops, and timeouts stop cyclic delegation before it becomes an incident.

Two runtimes as peers. A code agent and an Agentforce agent discover each other through a registry and delegate over A2A, with on-behalf-of identity and hop budgets enforced at the gateway.

Mermaid source

flowchart TD
  U["User on a surface"] --> G["Gateway: identity, policy, audit"]
  G --> B["Broker or registry: declared skills"]
  B --> AF["Agentforce agent: org-native step"]
  B --> CA["Code agent: SDK or LangGraph"]
  AF <--> CA
  CA --> T["MCP tools"]
  AF --> R["Salesforce records"]

In an org

A manufacturer.

The case step is org-native. The exception is not. Both are needed in the same process.

01The standard caseAgentforce answers the installed-base question, checks entitlement, and drafts the response inside the sharing model.

02The exceptionA part is discontinued and the spec sits in a supplier document. A code agent reads, reasons, and proposes a substitution with citations.

03The hand-offThe code agent returns a structured recommendation to the Agentforce agent over A2A. The service rep sees one thread.

04The writeThe substitution posts through the durable path, because the ERP has to accept it and a person has to be able to reverse it.

Step by step

Three processes, classified first.

Typical steps we mark before anyone picks a framework.

Example
Finance controller, Jeddah wholesaler
Today: Every invoice step goes through a model, including the ones with one right answer.
After: Matching stays a rule. Only the disputed line gets a model, with a person on the decision.
For CFOs
Example
CTO, Dubai logistics company
Today: The Agentforce agent and the Python agent cannot hand work over, so a dispatcher copies between two windows.
After: They delegate as peers over A2A through the gateway, with the user’s identity carried across.
Couriers and delivery
Example
Operations head, Riyadh equipment rental firm
Today: Every step runs through one product, so licence spend goes on work a plain function could do.
After: Each step is marked rule or judgement first. Rules stay in Flow. Judgement gets a runtime.
Agentforce or custom?

Examples of the work, not case studies. Roles and cities are typical of the desks we see.

How Mindcat helps

Where we would start in your org.

We classify the steps before anyone picks a framework. That conversation is short and it saves a quarter.

Questions

What we actually say.

Which SDK do you default to?: None. Multi-turn tool use with reflection before writes tends to be Claude. Structured routing tends to be OpenAI. Long cyclic work with approval gates tends to be LangGraph. The step decides.
Can Agentforce call our Python agent?: Yes, as a peer over A2A through the gateway, with the user’s identity carried across. Not as a shared key pointed at an internal URL.
Do you replace existing automation?: Not on day one. Deterministic automation that works stays. We move the steps that need judgement, and say which ones do not.

The brief · one email

Send one process, step by step.

We will mark which steps are deterministic and which deserve a model. The assessment is free: a short read of the org and a written note. If you go ahead, the first build week is a fixed AED/SAR 14,900 (about USD 4,050), credited in full when you sign the build within 60 days. The honest no: if the work is a software factory with a named delivery date, we are the wrong partner.