HarmonyFidelisHarmonyFidelis
Login
Skip to content
AURA
LearnConfigurePublic programs
Configure

Assistants & use cases

ChatGPT projectChoose your toolsInstructionsContext and memory

Development tools

Harness, tools and MCPSkills and workflows

Verification

Verify and develop

Explore each space independently. More detail is always within reach.

Aura home
AuraConfigure

Harness, tools and MCP

Prepare a development environment

Define the model’s role, harness capabilities and the access you actually need.

Model

Produces outputs from the available inputs.

Execution harness

Organises calls, task state, tools, permissions and stopping conditions.

Tools

File reading, changes or tests according to access actually granted.

Required capabilities

These checkboxes describe needs. They grant no access and change no account.

MCP

MCP organises exchanges between a host application, clients and servers. It replaces neither the model nor harness permissions. A simple task on supplied files does not necessarily need MCP.

Official documentation
  • OpenAI · Codex
  • OpenAI · AGENTS.md
  • Model Context Protocol
  • Anthropic · Claude Code

Harness brief

This JSON is an Aura educational specification, not a configuration file importable into ChatGPT, Codex or Claude. Map its needs to documented settings in the chosen product.

Your input stays in this tab. No assistant is connected.

Understand context and memory

Search Aura

18 results

LearnLearning, then using a modelSeparate learned parameters from information supplied with a request.
LearnFrom context to the next tokenSeparate the model’s probabilities from the rule that selects an output.
LearnFrom text to representationsUnderstand why words become vectors without equating a vector with human meaning.
LearnWhat kind of memory?Separate working context, recurrent state, learned parameters and persistent storage.
LearnTransformers: understanding attentionCompare architectures, training methods and complete systems at the right level.
LearnGenerating by denoisingDistinguish corruption during learning from progressive generation.
LearnFrom a model to a system that actsUnderstand the harness around a model and its tools.
LearnPredicting to choose an actionExplore longer horizons and the risk of inaccurate predictions.
LearnDefinitions, not a single verdictExamine generality, performance and adaptation before applying a label.
LearnWhat can a result establish?Move from a convincing impression to a reproducible comparison.
ConfigurePrepare a ChatGPT projectA clear objective, useful context and instructions you can actually use.
ConfigureChoose for your taskStart with your needs. Compare access and outcomes without a universal model ranking.
ConfigureMake your request verifiableTurn an intention into an objective, context and success criteria.
ConfigurePut the right information in the right placeDistinguish working rules, task resources and memory managed by the product.
ConfigurePrepare a development environmentDefine the model’s role, harness capabilities and the access you actually need.
ConfigureCompose a development workflowOrganise preparation, changes, verification and reporting. Reuse the steps that help.
ConfigurePrepare a mission, then check the resultA reproducible example, a checklist and a record of your observations.
Public programsTentacularPublicly available uses, features and resources.