Mechanism
Biological signal to forecasting coupling is a defined pathway by which biological signals from a human user modulate the forecasting engine's speculative reasoning. The signals include stress indicators, engagement levels, attention patterns, and physiological arousal metrics. The purpose is to make the agent's planning responsive to the user's current physiological and psychological state, so that the scope and character of the agent's speculative branches align with the user's capacity to engage with and benefit from the agent's actions.
The coupling acts on the planning graph, the first-class cognitive structure the forecasting engine constructs to represent hypothetical future states. It does not act on raw biosignals directly. A biological identity module acquires the signals, a processing pipeline reduces them to a structured biological state summary, and only that summary reaches the forecasting engine. The forecasting engine then applies the summary as a modulation input to a small, defined set of planning parameters before branches are generated and evaluated.
The coupling is one input among several. As described elsewhere in the forecasting disclosure, the personality field shapes the agent's slowly evolving disposition toward speculation and the affective state field shapes its rapidly changing dispositional orientation. Biological signal coupling sits alongside these as a further modulation source: it informs how the planning graph is built, but it does not by itself determine which branches may be promoted to execution.
The Biological State Summary
The biological identity module acquires biological signals from the human user through one of three signal acquisition modalities: contact, semi-contact, or non-contact. The biological signal processing pipeline extracts temporal dynamics and cross-signal coupling features from the raw signals and produces a structured biological state summary. The summary is what the forecasting engine consumes; the raw signal stream is not.
The biological state summary comprises three indicators. A stress indicator encodes the user's current physiological stress level. An engagement indicator encodes the user's current attentional engagement with the agent's operational context. A cognitive load indicator encodes the user's current cognitive processing burden as estimated from the biological signal features. These three indicators are the canonical content of the summary, and they are the values the forecasting engine reads.
The summary is transmitted to the forecasting engine through a defined coupling interface. The interface is the boundary between the biological identity subsystem and the cognitive substrate: it carries the abstracted indicators across, and it enforces the limits that the policy configuration places on how strongly those indicators may influence planning.
Modulation of Planning Horizon and Risk Tolerance
The forecasting engine applies the biological state summary to two specific parameters: the planning horizon and the risk tolerance. The planning horizon is the depth to which speculative branches are projected into the hypothetical future. The risk tolerance is the agent's willingness to generate and retain branches with high-variance projected outcomes. These two parameters are the targets of biological modulation; the coupling does not reach into the rest of the forecasting execution cycle.
When the user's stress indicator is elevated, the forecasting engine contracts the planning horizon, generating shorter, more conservative speculative branches that project near-term outcomes with higher confidence. When the user's engagement indicator is elevated, the forecasting engine expands the planning horizon, generating longer, more exploratory branches that project further into hypothetical futures. When the user's cognitive load indicator is elevated, the forecasting engine reduces risk tolerance, favoring branches with well-characterized, low-variance outcomes that minimize the cognitive burden on the user.
Each of these adjustments shapes branch generation and retention, not branch admissibility. A contracted horizon means the engine builds shallower branches; a reduced risk tolerance means it prefers branches with characterized outcomes and prunes uncertain ones more readily. The structural evaluation criteria that decide whether a branch may be promoted are unchanged by these adjustments.
Governance Separation
Biological signals modulate forecasting parameters but do not override governance requirements, policy constraints, or trust slope validation. The biological modulation operates within the same policy-bounded framework that governs all affective modulation. This is the same separation principle applied to the affective state field: modulation may change how the forecasting engine constructs and evaluates planning graphs, but it does not change whether a branch is admissible for promotion.
The policy configuration specifies the maximum magnitude of biological signal influence on planning parameters, and the coupling interface enforces these bounds. An elevated stress or cognitive load indicator can therefore make the agent plan more conservatively, but it cannot relax the slope eligibility check, the policy compatibility check, or any other promotion gate. A branch favored under biological modulation still has to pass the full governance evaluation before it can advance from speculative to verified status.
Privacy Governance
The coupling is privacy-governed. The biological signals are processed through the biological identity module's privacy governance framework, and the forecasting engine receives only the structured biological state summary, not raw biological data. The abstraction is structural, not incidental: the stress, engagement, and cognitive load indicators encode the user's current physiological condition without exposing biometric details.
The forecasting engine does not store, transmit, or record raw biological signals. It operates on the abstracted, privacy-compliant state summaries alone. This division of responsibility keeps the rich and privacy-sensitive raw signal stream confined to the biological identity subsystem, while the cognitive substrate works only with the reduced indicators it needs to modulate planning.
Acquisition Modalities
The biological signals that feed the summary are acquired through three tiers of modality, each producing signals of distinct quality. Contact-based acquisition requires deliberate physical interaction with a dedicated sensor and produces the highest signal quality. Semi-contact acquisition operates through wearable or body-proximate sensors that maintain sustained or intermittent contact without per-event interaction, producing moderate signal quality with continuous or near-continuous temporal coverage. Non-contact acquisition operates through ambient sensors that observe the user without physical contact, offering the broadest temporal coverage and the lowest interaction friction at lower per-measurement quality.
The semi-contact tier is the one most naturally suited to the forecasting coupling, because its sustained contact enables extraction of temporal dynamics, that is, how physiological signals evolve over seconds, minutes, and hours, which single-event contact captures cannot provide. The three tiers are not mutually exclusive; the architecture fuses signals across modalities and tiers under policy. Whichever modality or fusion is in use, the forecasting engine sees the same structured biological state summary, so the coupling does not depend on any specific acquisition method.
Composition with the Forecasting Engine
Biological signal coupling composes with the rest of the forecasting architecture by adjusting parameters that the forecasting execution cycle already uses. The planning horizon it contracts or expands is the same horizon that bounds speculative branch depth across the cycle. The risk tolerance it raises or lowers is the same personality-influenced parameter that governs how aggressively the engine generates and prunes high-variance branches. Because the coupling targets these existing parameters rather than introducing a parallel mechanism, no component downstream of branch generation needs to know that biology was a modulation source.
The coupling also sits cleanly beside the other modulation sources. The personality field, the affective state field, and the biological state summary all shape planning graph construction and evaluation within the same policy-bounded framework, and all of them stop at the same governance boundary. This shared discipline is what lets a biological input adjust the agent's planning posture without disturbing the trust and provenance guarantees that the promotion pathway enforces.
Disclosure Scope
The biological signal to forecasting coupling, comprising the acquisition of biological signals through contact, semi-contact, or non-contact modalities, the processing of those signals into a structured biological state summary of stress, engagement, and cognitive load indicators, the transmission of that summary to the forecasting engine through a defined coupling interface, the modulation of the planning horizon and risk tolerance by the stress, engagement, and cognitive load indicators, the policy-bounded enforcement of the maximum magnitude of that influence, the governance separation by which biological signals do not override policy constraints or trust slope validation, and the privacy governance by which the forecasting engine receives only the abstracted summary and never raw biological data, is disclosed in the cognition filing (U.S. Application No. 19/647,395 and its international counterpart). This article describes that disclosed mechanism. The scope is not limited to any specific acquisition modality and contemplates fused multi-modality signal sources, provided the forecasting engine consumes only the structured biological state summary and the modulation remains within the policy-bounded framework that governs all affective modulation.
